Abstract

The MuP-2022 shared task focuses on multiperspective scientific document summarization. Given a scientific document, with multiple reference summaries, our goal was to develop a model that can produce a generic summary covering as many aspects of the document as covered by all of its reference summaries. This paper describes our best official model, a finetuned BART-large, along with a discussion on the challenges of this task and some of our unofficial models including SOTA generation models. Our submitted model out performedthe given, MuP 2022 shared task, baselines on ROUGE-2, ROUGE-L and average ROUGE F1-scores. Code of our submission can be ac-cessed here.

Abstract

A system for generating a queryable structured document from an unstructured document using a machine learning model is provided . The system ( i ) identifies breakpoints in the unstructured document ,( ii ) segments the unstructured document into one or more fragments based on identified breakpoints , ( iii ) classifies the one or more fragments as one or more title fragments or one or more non - title fragments based on a sequence of a position of words used in each fragment of the one or more fragments , ( iv ) constructs a data tree using the one or more title fragments and the one or more non - title fragments as a node of the ata tree ; ( v ) assigns one or more vectors to each node of the data tree , and ( vi ) generates a structured document by providing matrix representation for each node of the data tree .

Abstract

Creating challenging tabular inference data is essential for learning complex reasoning. Prior work has mostly relied on two data generation strategies. The first is human annotation, which yields linguistically diverse data but is difficult to scale. The second category for creation is synthetic generation, which is scalable and cost effective but lacks inventiveness. In this research, we present a framework for semi-automatically recasting existing tabular data to make use of the benefits of both approaches. We utilize our framework to build tabular NLI instances from five datasets that were initially intended for tasks like table2text creation, tabular Q/A, and semantic parsing. We demonstrate that recasted data could be used as evaluation benchmarks as well as augmentation data to enhance performance on tabular NLI tasks. Furthermore, we investigate the effectiveness of models trained on recasted data in the zero-shot scenario, and analyse trends in performance across different recasted datasets types.

Abstract

Often questions provided to open-domain question answering systems are ambiguous. Traditional QA systems that provide a single answer are incapable of answering ambiguous questions since the question may be interpreted in several ways and may have multiple distinct answers. In this paper, we address multi-answer retrieval which entails retrieving passages that can capture majority of the diverse answers to the question. We propose a re-ranking based approach using Determinantal point processes utilizing BERT as kernels. Our method jointly considers query-passage relevance and passage-passage correlation to retrieve passages that are both query-relevant and diverse. Results demonstrate that our reranking technique outperforms state-of-the-art method on the AmbigQA dataset.

Abstract

This paper aims to provide an unsupervised modelling approach that allows for a more flexible representation of text embeddings. It jointly encodes the words and the paragraphs as individual matrices of arbitrary column dimension with unit Frobenius norm. The representation is also linguistically motivated with the introduction of a novel similarity metric. The proposed modelling and the novel similarity metric exploits the matrix structure of embeddings. We then go on to show that the same matrices can be reshaped into vectors of unit norm and transform our problem into an optimization problem over the spherical manifold. We exploit manifold optimization to efficiently train the matrix embeddings. We also quantitatively verify the quality of our text embeddings by showing that they demonstrate improved results in document classification, document clustering, and semantic textual similarity benchmark tests.

Abstract

Causality detection and identification is centered on identifying semantic and cognitive connections in a sentence. In this paper, we describe the effort of team LTRC for Causal News Corpus - Event Causality Shared Task 2022 at the 5th Workshop on Challenges and Applications of Automated Extraction of Sociopolitical Events from Text (CASE 2022) (Tan et al., 2022a). The shared task consisted of two subtasks: 1) identifying if a sentence contains a causality relation, and 2) identifying spans of text that correspond to cause, effect and signals. We fine-tuned transformer-based models with adapters for both subtasks. Our best-performing models obtained a binary F1 score of 0.853 on held-out data for subtask 1 and a macro F1 score of 0.032 on held-out data for subtask 2. Our approach is ranked third in subtask 1 and fourth in subtask 2. The paper describes our experiments, solutions, and analysis in detail.

Abstract

We present DocInfer-a novel, end-to-end Document-level Natural Language Inference model that builds a hierarchical document graph enriched through inter-sentence relations (topical, entity-based, concept-based), performs paragraph pruning using the novel SubGraph Pooling layer, followed by optimal evidence selection based on REINFORCE algorithm to identify the most important context sentences for a given hypothesis. Our evidence selection mechanism allows it to transcend the input length limitation of modern BERT-like Transformer models while presenting the entire evidence together for inferential reasoning. We show this is an important property needed to reason on large documents where the evidence may be fragmented and located arbitrarily far from each other. Extensive experiments on popular corpora-DocNLI, ContractNLI, and ConTRoL datasets, and our new proposed dataset called CaseHoldNLI on the task of legal judicial reasoning, demonstrate significant performance gains of 8-12% over SOTA methods. Our ablation studies validate the impact of our model. Performance improvement of 3-6% on annotation-scarce downstream tasks of fact verification, multiple-choice QA, and contract clause retrieval demonstrates the usefulness of DocInfer beyond primary NLI tasks.

Abstract

Code-mixing (CM) is a frequently observed phenomenon on social media platforms in mul- tilingual societies such as India. While the increase in code-mixed content on these plat- forms provides good amount of data for study- ing various aspects of code-mixing, the lack of automated text analysis tools makes such studies difficult. To overcome the same, tools such as language identifiers and parts of-speech (POS) taggers for analysing code-mixed data have been developed. One such tool is Named Entity Recognition (NER), an important Natu- ral Language Processing (NLP) task, which is not only a subtask of Information Extraction, but is also needed for downstream NLP tasks such as semantic role labeling. While entity extraction from social media data is generally difficult due to its informal nature, code-mixed data further complicates the problem due to its informal, unstructured and incomplete infor- mation. In this work, we present the first ever corpus for Kannada-English code-mixed social media data with the corresponding named en- tity tags for NER. We provide strong baselines with machine learning classification models such as CRF, Bi-LSTM, and Bi-LSTM-CRF on our corpus with word, character, and lexical features.

Abstract

Neural models command state-of-the-art per- formance across NLP tasks, including ones involving ‘‘reasoning’’. Models claiming to reason about the evidence presented to them should attend to the correct parts of the input while avoiding spurious patterns therein, be self-consistent in their predictions across in- puts, and be immune to biases derived from their pre-training in a nuanced, context- sensitive fashion. Do the prevalent *BERT- family of models do so? In this paper, we study this question using the problem of rea- soning on tabular data. Tabular inputs are especially well-suited for the study—they ad- mit systematic probes targeting the properties listed above. Our experiments demonstrate that a RoBERTa-based model, representative of the current state-of-the-art, fails at reason- ing on the following counts: it (a) ignores relevant parts of the evidence, (b) is over- sensitive to annotation artifacts, and (c) relies on the knowledge encoded in the pre-trained language model rather than the evidence pre- sented in its tabular inputs. Finally, through inoculation experiments, we show that fine- tuning the model on perturbed data does not help it overcome the above challenges.

Abstract

Character arcs are important theoretical devices employed in literary studies to understand character journeys, identify tropes across literary genres, and establish similarities between narratives. This work addresses the novel task of computationally generating event-centric, relation-based character arcs from narratives. Providing a quantitative representation for arcs brings tangibility to a theoretical concept and paves the way for subsequent applications. We present MARCUS (Modelling Arcs for Understanding Stories), an NLP pipeline that extracts events, participant characters, implied emotion, and sentiment to model inter-character relations. MARCUS tracks and aggregates these relations across the narrative to generate character arcs as graphical plots. We generate character arcs from two extended fantasy series, Harry Potter and Lord of the Rings. We evaluate our approach before outlining existing challenges, suggesting applications of our pipeline, and discussing future work