Computation and Language (cs.CL)

Abstract: Fine-tuning pre-trained language models (PLMs), e.g., SciBERT, generally requires large numbers of annotated data to achieve state-of-the-art performance on a range of NLP tasks in the scientific domain. However, obtaining the fine-tune data for scientific NLP task is still challenging and expensive. Inspired by recent advancement in prompt learning, in this paper, we propose the Mix Prompt Tuning (MPT), which is a semi-supervised method to alleviate the dependence on annotated data and improve the performance of multi-granularity academic function recognition tasks with a small number of labeled examples. Specifically, the proposed method provides multi-perspective representations by combining manual prompt templates with automatically learned continuous prompt templates to help the given academic function recognition task take full advantage of knowledge in PLMs. Based on these prompt templates and the fine-tuned PLM, a large number of pseudo labels are assigned to the unlabeled examples. Finally, we fine-tune the PLM using the pseudo training set. We evaluate our method on three academic function recognition tasks of different granularity including the citation function, the abstract sentence function, and the keyword function, with datasets from computer science domain and biomedical domain. Extensive experiments demonstrate the effectiveness of our method and statistically significant improvements against strong baselines. In particular, it achieves an average increase of 5% in Macro-F1 score compared with fine-tuning, and 6% in Macro-F1 score compared with other semi-supervised method under low-resource settings. In addition, MPT is a general method that can be easily applied to other low-resource scientific classification tasks.

Abstract: Emotion Support Conversation (ESC) is an emerging and challenging task with the goal of reducing the emotional distress of people. Previous attempts fail to maintain smooth transitions between utterances in ESC because they ignore to grasp the fine-grained transition information at each dialogue turn. To solve this problem, we propose to take into account turn-level state \textbf{Trans}itions of \textbf{ESC} (\textbf{TransESC}) from three perspectives, including semantics transition, strategy transition and emotion transition, to drive the conversation in a smooth and natural way. Specifically, we construct the state transition graph with a two-step way, named transit-then-interact, to grasp such three types of turn-level transition information. Finally, they are injected into the transition-aware decoder to generate more engaging responses. Both automatic and human evaluations on the benchmark dataset demonstrate the superiority of TransESC to generate more smooth and effective supportive responses. Our source code is available at \url{https://github.com/circle-hit/TransESC}.

Abstract: Open Information Extraction (OIE) aims to extract relational tuples from open-domain sentences. Existing OIE systems split a sentence into tokens and recognize token spans as tuple relations and arguments. We instead propose Sentence as Chunk sequence (SaC) and recognize chunk spans as tuple relations and arguments. We argue that SaC has better quantitative and qualitative properties for OIE than sentence as token sequence, and evaluate four choices of chunks (i.e., CoNLL chunks, simple phrases, NP chunks, and spans from SpanOIE) against gold OIE tuples. Accordingly, we propose a simple BERT-based model for sentence chunking, and propose Chunk-OIE for tuple extraction on top of SaC. Chunk-OIE achieves state-of-the-art results on multiple OIE datasets, showing that SaC benefits OIE task.

Abstract: Named Entity Recognition(NER) is a task of recognizing entities at a token level in a sentence. This paper focuses on solving NER tasks in a multilingual setting for complex named entities. Our team, LLM-RM participated in the recently organized SemEval 2023 task, Task 2: MultiCoNER II,Multilingual Complex Named Entity Recognition. We approach the problem by leveraging cross-lingual representation provided by fine-tuning XLM-Roberta base model on datasets of all of the 12 languages provided -- Bangla, Chinese, English, Farsi, French, German, Hindi, Italian, Portuguese, Spanish, Swedish and Ukrainian

Abstract: Recently, Chinese Spell Checking(CSC), a task to detect erroneous characters in a sentence and correct them, has attracted extensive interest because of its wide applications in various NLP tasks. Most of the existing methods have utilized BERT to extract semantic information for CSC task. However, these methods directly take sentences with only a few errors as inputs, where the correct characters may leak answers to the model and dampen its ability to capture distant context; while the erroneous characters may disturb the semantic encoding process and result in poor representations. Based on such observations, this paper proposes an n-gram masking layer that masks current and/or surrounding tokens to avoid label leakage and error disturbance. Moreover, considering that the mask strategy may ignore multi-modal information indicated by errors, a novel dot-product gating mechanism is proposed to integrate the phonological and morphological information with semantic representation. Extensive experiments on SIGHAN datasets have demonstrated that the pluggable n-gram masking mechanism can improve the performance of prevalent CSC models and the proposed methods in this paper outperform multiple powerful state-of-the-art models.

Abstract: Encoding long sequences in Natural Language Processing (NLP) is a challenging problem. Though recent pretraining language models achieve satisfying performances in many NLP tasks, they are still restricted by a pre-defined maximum length, making them challenging to be extended to longer sequences. So some recent works utilize hierarchies to model long sequences. However, most of them apply sequential models for upper hierarchies, suffering from long dependency issues. In this paper, we alleviate these issues through a graph-based method. We first chunk the sequence with a fixed length to model the sentence-level information. We then leverage graphs to model intra- and cross-sentence correlations with a new attention mechanism. Additionally, due to limited standard benchmarks for long document classification (LDC), we propose a new challenging benchmark, totaling six datasets with up to 53k samples and 4034 average tokens' length. Evaluation shows our model surpasses competitive baselines by 2.6% in F1 score, and 4.8% on the longest sequence dataset. Our method is shown to outperform hierarchical sequential models with better performance and scalability, especially for longer sequences.

Abstract: Misinformation spreading in mainstream and social media has been misleading users in different ways. Manual detection and verification efforts by journalists and fact-checkers can no longer cope with the great scale and quick spread of misleading information. This motivated research and industry efforts to develop systems for analyzing and verifying news spreading online. The SemEval-2023 Task 3 is an attempt to address several subtasks under this overarching problem, targeting writing techniques used in news articles to affect readers' opinions. The task addressed three subtasks with six languages, in addition to three ``surprise'' test languages, resulting in 27 different test setups. This paper describes our participating system to this task. Our team is one of the 6 teams that successfully submitted runs for all setups. The official results show that our system is ranked among the top 3 systems for 10 out of the 27 setups.

Abstract: Theory of Mind (ToM) is a critical component of intelligence, yet accurately measuring it continues to be a subject of debate. Prior research has attempted to apply human ToM assessments to natural language processing models using either human-created standardized tests or rule-based templates. However, these methods primarily focus on simplistic reasoning and require further validation. In this study, we utilize dynamic epistemic logic, which has established overlaps with ToM, to generate more intricate problems. We also introduce novel verbalization techniques to express these problems using natural language. Our findings indicate that certain language model scaling (from 70M to 6B and 350M to 174B) does not consistently yield results better than random chance. While GPT-4 demonstrates improved epistemic reasoning capabilities, there is still room for enhancement. Our code and datasets are publicly available https://github.com/antoinelrnld/modlog https://huggingface.co/datasets/sileod/mindgames

Abstract: Parsing questions into executable logical forms has showed impressive results for knowledge-base question answering (KBQA). However, complex KBQA is a more challenging task that requires to perform complex multi-step reasoning. Recently, a new semantic parser called KoPL has been proposed to explicitly model the reasoning processes, which achieved the state-of-the-art on complex KBQA. In this paper, we further explore how to unlock the reasoning ability of semantic parsers by a simple proposed parse-execute-refine paradigm. We refine and improve the KoPL parser by demonstrating the executed intermediate reasoning steps to the KBQA model. We show that such simple strategy can significantly improve the ability of complex reasoning. Specifically, we propose three components: a parsing stage, an execution stage and a refinement stage, to enhance the ability of complex reasoning. The parser uses the KoPL to generate the transparent logical forms. Then, the execution stage aligns and executes the logical forms over knowledge base to obtain intermediate reasoning processes. Finally, the intermediate step-by-step reasoning processes are demonstrated to the KBQA model in the refinement stage. With the explicit reasoning processes, it is much easier to answer the complex questions. Experiments on benchmark dataset shows that the proposed PER-KBQA performs significantly better than the stage-of-the-art baselines on the complex KBQA.

Abstract: The Transformer architecture is shown to provide a powerful machine transduction framework for online handwritten gestures corresponding to glyph strokes of natural language sentences. The attention mechanism is successfully used to create latent representations of an end-to-end encoder-decoder model, solving multi-level segmentation while also learning some language features and syntax rules. The additional use of a large decoding space with some learned Byte-Pair-Encoding (BPE) is shown to provide robustness to ablated inputs and syntax rules. The encoder stack was directly fed with spatio-temporal data tokens potentially forming an infinitely large input vocabulary, an approach that finds applications beyond that of this work. Encoder transfer learning capabilities is also demonstrated on several languages resulting in faster optimisation and shared parameters. A new supervised dataset of online handwriting gestures suitable for generic handwriting recognition tasks was used to successfully train a small transformer model to an average normalised Levenshtein accuracy of 96% on English or German sentences and 94% in French.

Abstract: Entity Matching is the task of deciding if two entity descriptions refer to the same real-world entity. State-of-the-art entity matching methods often rely on fine-tuning Transformer models such as BERT or RoBERTa. Two major drawbacks of using these models for entity matching are that (i) the models require significant amounts of fine-tuning data for reaching a good performance and (ii) the fine-tuned models are not robust concerning out-of-distribution entities. In this paper, we investigate using ChatGPT for entity matching as a more robust, training data-efficient alternative to traditional Transformer models. We perform experiments along three dimensions: (i) general prompt design, (ii) in-context learning, and (iii) provision of higher-level matching knowledge. We show that ChatGPT is competitive with a fine-tuned RoBERTa model, reaching an average zero-shot performance of 83% F1 on a challenging matching task on which RoBERTa requires 2000 training examples for reaching a similar performance. Adding in-context demonstrations to the prompts further improves the F1 by up to 5% even using only a small set of 20 handpicked examples. Finally, we show that guiding the zero-shot model by stating higher-level matching rules leads to similar gains as providing in-context examples.

Abstract: In this paper, we present a novel approach to simulating H.P. Lovecraft's horror literature using the ChatGPT large language model, specifically the GPT-4 architecture. Our study aims to generate text that emulates Lovecraft's unique writing style and themes, while also examining the effectiveness of prompt engineering techniques in guiding the model's output. To achieve this, we curated a prompt containing several specialized literature references and employed advanced prompt engineering methods. We conducted an empirical evaluation of the generated text by administering a survey to a sample of undergraduate students. Utilizing statistical hypothesis testing, we assessed the students ability to distinguish between genuine Lovecraft works and those generated by our model. Our findings demonstrate that the participants were unable to reliably differentiate between the two, indicating the effectiveness of the GPT-4 model and our prompt engineering techniques in emulating Lovecraft's literary style. In addition to presenting the GPT model's capabilities, this paper provides a comprehensive description of its underlying architecture and offers a comparative analysis with related work that simulates other notable authors and philosophers, such as Dennett. By exploring the potential of large language models in the context of literary emulation, our study contributes to the body of research on the applications and limitations of these models in various creative domains.

Abstract: Figurative language is a challenge for language models since its interpretation is based on the use of words in a way that deviates from their conventional order and meaning. Yet, humans can easily understand and interpret metaphors, similes or idioms as they can be derived from embodied metaphors. Language is a proxy for embodiment and if a metaphor is conventional and lexicalised, it becomes easier for a system without a body to make sense of embodied concepts. Yet, the intricate relation between embodiment and features such as concreteness or age of acquisition has not been studied in the context of figurative language interpretation concerning language models. Hence, the presented study shows how larger language models perform better at interpreting metaphoric sentences when the action of the metaphorical sentence is more embodied. The analysis rules out multicollinearity with other features (e.g. word length or concreteness) and provides initial evidence that larger language models conceptualise embodied concepts to a degree that facilitates figurative language understanding.

Abstract: Large Language Models (LLMs) have recently demonstrated exceptional performance in various Natural Language Processing (NLP) tasks. They have also shown the ability to perform chain-of-thought (CoT) reasoning to solve complex problems. Recent studies have explored CoT reasoning in complex multimodal scenarios, such as the science question answering task, by fine-tuning multimodal models with high-quality human-annotated CoT rationales. However, collecting high-quality COT rationales is usually time-consuming and costly. Besides, the annotated rationales are hardly accurate due to the redundant information involved or the essential information missed. To address these issues, we propose a novel method termed \emph{T-SciQ} that aims at teaching science question answering with LLM signals. The T-SciQ approach generates high-quality CoT rationales as teaching signals and is advanced to train much smaller models to perform CoT reasoning in complex modalities. Additionally, we introduce a novel data mixing strategy to produce more effective teaching data samples for simple and complex science question answer problems. Extensive experimental results show that our T-SciQ method achieves a new state-of-the-art performance on the ScienceQA benchmark, with an accuracy of 96.18%. Moreover, our approach outperforms the most powerful fine-tuned baseline by 4.5%.

Abstract: Hybrid question answering (HybridQA) over the financial report contains both textual and tabular data, and requires the model to select the appropriate evidence for the numerical reasoning task. Existing methods based on encoder-decoder framework employ a expression tree-based decoder to solve numerical reasoning problems. However, encoders rely more on Machine Reading Comprehension (MRC) methods, which take table serialization and text splicing as input, damaging the granularity relationship between table and text as well as the spatial structure information of table itself. In order to solve these problems, the paper proposes a Multi-View Graph (MVG) Encoder to take the relations among the granularity into account and capture the relations from multiple view. By utilizing MVGE as a module, we constuct Tabular View, Relation View and Numerical View which aim to retain the original characteristics of the hybrid data. We validate our model on the publicly available table-text hybrid QA benchmark (TAT-QA) and outperform the state-of-the-art model.

Abstract: Interactive Task Learning (ITL) concerns learning about unforeseen domain concepts via natural interactions with human users. The learner faces a number of significant constraints: learning should be online, incremental and few-shot, as it is expected to perform tangible belief updates right after novel words denoting unforeseen concepts are introduced. In this work, we explore a challenging symbol grounding task--discriminating among object classes that look very similar--within the constraints imposed by ITL. We demonstrate empirically that more data-efficient grounding results from exploiting the truth-conditions of the teacher's generic statements (e.g., "Xs have attribute Z.") and their implicatures in context (e.g., as an answer to "How are Xs and Ys different?", one infers Y lacks attribute Z).

Abstract: The issue of word sense ambiguity poses a significant challenge in natural language processing due to the scarcity of annotated data to feed machine learning models to face the challenge. Therefore, unsupervised word sense disambiguation methods have been developed to overcome that challenge without relying on annotated data. This research proposes a new context-aware approach to unsupervised word sense disambiguation, which provides a flexible mechanism for incorporating contextual information into the similarity measurement process. We experiment with a popular benchmark dataset to evaluate the proposed strategy and compare its performance with state-of-the-art unsupervised word sense disambiguation techniques. The experimental results indicate that our approach substantially enhances disambiguation accuracy and surpasses the performance of several existing techniques. Our findings underscore the significance of integrating contextual information in semantic similarity measurements to manage word sense ambiguity in unsupervised scenarios effectively.

Abstract: The phenomena of in-context learning has typically been thought of as "learning from examples". In this work which focuses on Machine Translation, we present a perspective of in-context learning as the desired generation task maintaining coherency with its context, i.e., the prompt examples. We first investigate randomly sampled prompts across 4 domains, and find that translation performance improves when shown in-domain prompts. Next, we investigate coherency for the in-domain setting, which uses prompt examples from a moving window. We study this with respect to other factors that have previously been identified in the literature such as length, surface similarity and sentence embedding similarity. Our results across 3 models (GPTNeo2.7B, Bloom3B, XGLM2.9B), and three translation directions (\texttt{en}$\rightarrow$\{\texttt{pt, de, fr}\}) suggest that the long-term coherency of the prompts and the test sentence is a good indicator of downstream translation performance. In doing so, we demonstrate the efficacy of In-context Machine Translation for on-the-fly adaptation.

Abstract: In recent years, Federated Learning (FL) has shown significant advancements in its ability to perform various natural language processing (NLP) tasks. This work focuses on applying personalized FL for on-device language modeling. Due to limitations of memory and latency, these models cannot support the complexity of sub-word tokenization or beam search decoding, resulting in the decision to deploy a closed-vocabulary language model. However, closed-vocabulary models are unable to handle out-of-vocabulary (OOV) words belonging to specific users. To address this issue, We propose a novel technique called "OOV expansion" that improves OOV coverage and increases model accuracy while minimizing the impact on memory and latency. This method introduces a personalized "OOV adapter" that effectively transfers knowledge from a central model and learns word embedding for personalized vocabulary. OOV expansion significantly outperforms standard FL personalization methods on a set of common FL benchmarks.

Abstract: How can we interpret and retrieve medical evidence to support clinical decisions? Clinical trial reports (CTR) amassed over the years contain indispensable information for the development of personalized medicine. However, it is practically infeasible to manually inspect over 400,000+ clinical trial reports in order to find the best evidence for experimental treatments. Natural Language Inference (NLI) offers a potential solution to this problem, by allowing the scalable computation of textual entailment. However, existing NLI models perform poorly on biomedical corpora, and previously published datasets fail to capture the full complexity of inference over CTRs. In this work, we present a novel resource to advance research on NLI for reasoning on CTRs. The resource includes two main tasks. Firstly, to determine the inference relation between a natural language statement, and a CTR. Secondly, to retrieve supporting facts to justify the predicted relation. We provide NLI4CT, a corpus of 2400 statements and CTRs, annotated for these tasks. Baselines on this corpus expose the limitations of existing NLI models, with 6 state-of-the-art NLI models achieving a maximum F1 score of 0.627. To the best of our knowledge, we are the first to design a task that covers the interpretation of full CTRs. To encourage further work on this challenging dataset, we make the corpus, competition leaderboard, website and code to replicate the baseline experiments available at: https://github.com/ai-systems/nli4ct

Abstract: Results from Randomized Controlled Trials (RCTs) establish the comparative effectiveness of interventions, and are in turn critical inputs for evidence-based care. However, results from RCTs are presented in (often unstructured) natural language articles describing the design, execution, and outcomes of trials; clinicians must manually extract findings pertaining to interventions and outcomes of interest from such articles. This onerous manual process has motivated work on (semi-)automating extraction of structured evidence from trial reports. In this work we propose and evaluate a text-to-text model built on instruction-tuned Large Language Models (LLMs) to jointly extract Interventions, Outcomes, and Comparators (ICO elements) from clinical abstracts, and infer the associated results reported. Manual (expert) and automated evaluations indicate that framing evidence extraction as a conditional generation task and fine-tuning LLMs for this purpose realizes considerable ($\sim$20 point absolute F1 score) gains over the previous SOTA. We perform ablations and error analyses to assess aspects that contribute to model performance, and to highlight potential directions for further improvements. We apply our model to a collection of published RCTs through mid-2022, and release a searchable database of structured findings (anonymously for now): bit.ly/joint-relations-extraction-mlhc

Abstract: Pre-trained transformers are popular in state-of-the-art dialogue generation (DG) systems. Such language models are, however, vulnerable to various adversarial samples as studied in traditional tasks such as text classification, which inspires our curiosity about their robustness in DG systems. One main challenge of attacking DG models is that perturbations on the current sentence can hardly degrade the response accuracy because the unchanged chat histories are also considered for decision-making. Instead of merely pursuing pitfalls of performance metrics such as BLEU, ROUGE, we observe that crafting adversarial samples to force longer generation outputs benefits attack effectiveness -- the generated responses are typically irrelevant, lengthy, and repetitive. To this end, we propose a white-box multi-objective attack method called DGSlow. Specifically, DGSlow balances two objectives -- generation accuracy and length, via a gradient-based multi-objective optimizer and applies an adaptive searching mechanism to iteratively craft adversarial samples with only a few modifications. Comprehensive experiments on four benchmark datasets demonstrate that DGSlow could significantly degrade state-of-the-art DG models with a higher success rate than traditional accuracy-based methods. Besides, our crafted sentences also exhibit strong transferability in attacking other models.

Abstract: We propose Retrieval Augmented Generation (RAG) as an approach for automated radiology report writing that leverages multimodally aligned embeddings from a contrastively pretrained vision language model for retrieval of relevant candidate radiology text for an input radiology image and a general domain generative model like OpenAI text-davinci-003, gpt-3.5-turbo and gpt-4 for report generation using the relevant radiology text retrieved. This approach keeps hallucinated generations under check and provides capabilities to generate report content in the format we desire leveraging the instruction following capabilities of these generative models. Our approach achieves better clinical metrics with a BERTScore of 0.2865 ({\Delta}+ 25.88%) and Semb score of 0.4026 ({\Delta}+ 6.31%). Our approach can be broadly relevant for different clinical settings as it allows to augment the automated radiology report generation process with content relevant for that setting while also having the ability to inject user intents and requirements in the prompts as part of the report generation process to modulate the content and format of the generated reports as applicable for that clinical setting.

Abstract: In this paper we present a novel approach to risk assessment for patients hospitalized with pneumonia or COVID-19 based on their admission reports. We applied a Longformer neural network to admission reports and other textual data available shortly after admission to compute risk scores for the patients. We used patient data of multiple European hospitals to demonstrate that our approach outperforms the Transformer baselines. Our experiments show that the proposed model generalises across institutions and diagnoses. Also, our method has several other advantages described in the paper.

Abstract: Webpages have been a rich, scalable resource for vision-language and language only tasks. Yet only pieces of webpages are kept: image-caption pairs, long text articles, or raw HTML, never all in one place. Webpage tasks have resultingly received little attention and structured image-text data left underused. To study multimodal webpage understanding, we introduce the Wikipedia Webpage suite (WikiWeb2M) of 2M pages. We verify its utility on three generative tasks: page description generation, section summarization, and contextual image captioning. We design a novel attention mechanism Prefix Global, which selects the most relevant image and text content as global tokens to attend to the rest of the webpage for context. By using page structure to separate such tokens, it performs better than full attention with lower computational complexity. Experiments show that the new annotations from WikiWeb2M improve task performance compared to data from prior work. We also include ablations on sequence length, input features, and model size.

Abstract: The MultiCoNER \RNum{2} shared task aims to tackle multilingual named entity recognition (NER) in fine-grained and noisy scenarios, and it inherits the semantic ambiguity and low-context setting of the MultiCoNER \RNum{1} task. To cope with these problems, the previous top systems in the MultiCoNER \RNum{1} either incorporate the knowledge bases or gazetteers. However, they still suffer from insufficient knowledge, limited context length, single retrieval strategy. In this paper, our team \textbf{DAMO-NLP} proposes a unified retrieval-augmented system (U-RaNER) for fine-grained multilingual NER. We perform error analysis on the previous top systems and reveal that their performance bottleneck lies in insufficient knowledge. Also, we discover that the limited context length causes the retrieval knowledge to be invisible to the model. To enhance the retrieval context, we incorporate the entity-centric Wikidata knowledge base, while utilizing the infusion approach to broaden the contextual scope of the model. Also, we explore various search strategies and refine the quality of retrieval knowledge. Our system\footnote{We will release the dataset, code, and scripts of our system at {\small \url{https://github.com/modelscope/AdaSeq/tree/master/examples/U-RaNER}}.} wins 9 out of 13 tracks in the MultiCoNER \RNum{2} shared task. Additionally, we compared our system with ChatGPT, one of the large language models which have unlocked strong capabilities on many tasks. The results show that there is still much room for improvement for ChatGPT on the extraction task.

Abstract: Despite the much discussed capabilities of today's language models, they are still prone to silly and unexpected commonsense failures. We consider a retrospective verification approach that reflects on the correctness of LM outputs, and introduce Vera, a general-purpose model that estimates the plausibility of declarative statements based on commonsense knowledge. Trained on ~7M commonsense statements created from 19 QA datasets and two large-scale knowledge bases, and with a combination of three training objectives, Vera is a versatile model that effectively separates correct from incorrect statements across diverse commonsense domains. When applied to solving commonsense problems in the verification format, Vera substantially outperforms existing models that can be repurposed for commonsense verification, and it further exhibits generalization capabilities to unseen tasks and provides well-calibrated outputs. We find that Vera excels at filtering LM-generated commonsense knowledge and is useful in detecting erroneous commonsense statements generated by models like ChatGPT in real-world settings.

Abstract: This study investigates the potential of an ambulatory device that incorporates Large Language Models (LLMs) in cadence with other specialized ML models to assess anemia severity in sickle cell patients in real time. The device would rely on sensor data that measures angiogenic material levels to assess anemia severity, providing real-time information to patients and clinicians to reduce the frequency of vaso-occlusive crises because of the early detection of anemia severity, allowing for timely interventions and potentially reducing the likelihood of serious complications. The main challenges in developing such a device are the creation of a reliable non-invasive tool for angiogenic level assessment, a biophysics model and the practical consideration of an LLM communicating with emergency personnel on behalf of an incapacitated patient. A possible system is proposed, and the limitations of this approach are discussed.