arXiv subjects

Prafulla Kumar Choubey

Publications and source records attributed to Prafulla Kumar Choubey.

29 records · Page 2Linked to original sources

arXiv2022

Improving Factual Consistency in Summarization with Compression-Based Post-Editing

State-of-the-art summarization models still struggle to be factually consistent with the input text. A model-agnostic way to address this problem is post-editing the generated summaries. However, existing approaches typically fail to remove entity errors if a suitable input entity replacement is not available or may insert erroneous content. In our work, we focus on removing extrinsic entity errors, or entities not in the source, to improve consistency while retaining the summary's essential information and form. We propose to use sentence-compression data to train the post-editing model to take a summary with extrinsic entity errors marked with special tokens and output a compressed, well-formed summary with those errors removed. We show that this model improves factual consistency while maintaining ROUGE, improving entity precision by up to 30% on XSum, and that this model can be applied on top of another post-editor, improving entity precision by up to a total of 38%. We perform an extensive comparison of post-editing approaches that demonstrate trade-offs between factual consistency, informativeness, and grammaticality, and we analyze settings where post-editors show the largest improvements.

cs.CL↗

arXiv2022

Conformal Predictor for Improving Zero-shot Text Classification Efficiency

Pre-trained language models (PLMs) have been shown effective for zero-shot (0shot) text classification. 0shot models based on natural language inference (NLI) and next sentence prediction (NSP) employ cross-encoder architecture and infer by making a forward pass through the model for each label-text pair separately. This increases the computational cost to make inferences linearly in the number of labels. In this work, we improve the efficiency of such cross-encoder-based 0shot models by restricting the number of likely labels using another fast base classifier-based conformal predictor (CP) calibrated on samples labeled by the 0shot model. Since a CP generates prediction sets with coverage guarantees, it reduces the number of target labels without excluding the most probable label based on the 0shot model. We experiment with three intent and two topic classification datasets. With a suitable CP for each dataset, we reduce the average inference time for NLI- and NSP-based models by 25.6% and 22.2% respectively, without dropping performance below the predefined error rate of 1%.

cs.CL↗

arXiv2022

Modeling Document-level Temporal Structures for Building Temporal Dependency Graphs

We propose to leverage news discourse profiling to model document-level temporal structures for building temporal dependency graphs. Our key observation is that the functional roles of sentences used for profiling news discourse signify different time frames relevant to a news story and can, therefore, help to recover the global temporal structure of a document. Our analyses and experiments with the widely used knowledge distillation technique show that discourse profiling effectively identifies distant inter-sentence event and (or) time expression pairs that are temporally related and otherwise difficult to locate.

cs.CL↗

arXiv2022

CaPE: Contrastive Parameter Ensembling for Reducing Hallucination in Abstractive Summarization

Hallucination is a known issue for neural abstractive summarization models. Recent work suggests that the degree of hallucination may depend on errors in the training data. In this work, we propose a new method called Contrastive Parameter Ensembling (CaPE) to use training data more effectively, utilizing variations in noise in training samples to reduce hallucination. We first select clean and noisy subsets from the training data using different automatic factual metrics. Then, we fine-tune a base summarization model, which is trained on all training samples, on the clean (noisy) subset to obtain an \textit{expert} (\textit{anti-expert}) model. Finally, we adjust the parameters of base model by the difference between parameters of the \textit{expert} and \textit{anti-expert} models, steering the base model towards the \textit{expert} model and away from the \textit{anti-expert} model. Experimental results show that CaPE improves performance across different automatic factual metrics and human evaluation, with the maximum improvement of 16.69\% and 15.78\% on summary-level dependency-arc entailment accuracy for the XSUM and CNN/DM datasets. The improvement in factual performance does not degrade the performance on other metrics of informativeness such as ROUGE.

cs.CL↗

arXiv2022

P-Adapters: Robustly Extracting Factual Information from Language Models with Diverse Prompts

Recent work (e.g. LAMA (Petroni et al., 2019)) has found that the quality of the factual information extracted from Large Language Models (LLMs) depends on the prompts used to query them. This inconsistency is problematic because different users will query LLMs for the same information using different wording, but should receive the same, accurate responses regardless. In this work we aim to address this shortcoming by introducing P-Adapters: lightweight models that sit between the embedding layer and first attention layer of LLMs. They take LLM embeddings as input and output continuous prompts that are used to query the LLM. Additionally, we investigate Mixture of Experts (MoE) models that learn a set of continuous prompts ("experts") and select one to query the LLM. They require a separate classifier trained on human-annotated data to map natural language prompts to the continuous ones. P-Adapters perform comparably to the more complex MoE models in extracting factual information from BERT and RoBERTa while eliminating the need for additional annotations. P-Adapters show between 12-26% absolute improvement in precision and 36-50% absolute improvement in consistency over a baseline of only using natural language queries. Finally, we investigate what makes P-Adapters successful and conclude that a significant factor is access to the LLM's embeddings of the original natural language prompt, particularly the subject of the entity pair being queried.

cs.CL↗

arXiv2021

Improving Gender Translation Accuracy with Filtered Self-Training

Targeted evaluations have found that machine translation systems often output incorrect gender, even when the gender is clear from context. Furthermore, these incorrectly gendered translations have the potential to reflect or amplify social biases. We propose a gender-filtered self-training technique to improve gender translation accuracy on unambiguously gendered inputs. This approach uses a source monolingual corpus and an initial model to generate gender-specific pseudo-parallel corpora which are then added to the training data. We filter the gender-specific corpora on the source and target sides to ensure that sentence pairs contain and correctly translate the specified gender. We evaluate our approach on translation from English into five languages, finding that our models improve gender translation accuracy without any cost to generic translation quality. In addition, we show the viability of our approach on several settings, including re-training from scratch, fine-tuning, controlling the balance of the training data, forward translation, and back-translation.

cs.CL↗

arXiv2019

In Plain Sight: Media Bias Through the Lens of Factual Reporting

The increasing prevalence of political bias in news media calls for greater public awareness of it, as well as robust methods for its detection. While prior work in NLP has primarily focused on the lexical bias captured by linguistic attributes such as word choice and syntax, other types of bias stem from the actual content selected for inclusion in the text. In this work, we investigate the effects of informational bias: factual content that can nevertheless be deployed to sway reader opinion. We first produce a new dataset, BASIL, of 300 news articles annotated with 1,727 bias spans and find evidence that informational bias appears in news articles more frequently than lexical bias. We further study our annotations to observe how informational bias surfaces in news articles by different media outlets. Lastly, a baseline model for informational bias prediction is presented by fine-tuning BERT on our labeled data, indicating the challenges of the task and future directions.

cs.CL↗

arXiv2019

Improving Dialogue State Tracking by Discerning the Relevant Context

A typical conversation comprises of multiple turns between participants where they go back-and-forth between different topics. At each user turn, dialogue state tracking (DST) aims to estimate user's goal by processing the current utterance. However, in many turns, users implicitly refer to the previous goal, necessitating the use of relevant dialogue history. Nonetheless, distinguishing relevant history is challenging and a popular method of using dialogue recency for that is inefficient. We, therefore, propose a novel framework for DST that identifies relevant historical context by referring to the past utterances where a particular slot-value changes and uses that together with weighted system utterance to identify the relevant context. Specifically, we use the current user utterance and the most recent system utterance to determine the relevance of a system utterance. Empirical analyses show that our method improves joint goal accuracy by 2.75% and 2.36% on WoZ 2.0 and MultiWoZ 2.0 restaurant domain datasets respectively over the previous state-of-the-art GLAD model.

cs.CL↗

arXiv2018

TAMU at KBP 2017: Event Nugget Detection and Coreference Resolution

In this paper, we describe TAMU's system submitted to the TAC KBP 2017 event nugget detection and coreference resolution task. Our system builds on the statistical and empirical observations made on training and development data. We found that modifiers of event nuggets tend to have unique syntactic distribution. Their parts-of-speech tags and dependency relations provides them essential characteristics that are useful in identifying their span and also defining their types and realis status. We further found that the joint modeling of event span detection and realis status identification performs better than the individual models for both tasks. Our simple system designed using minimal features achieved the micro-average F1 scores of 57.72, 44.27 and 42.47 for event span detection, type identification and realis status classification tasks respectively. Also, our system achieved the CoNLL F1 score of 27.20 in event coreference resolution task.

cs.CL↗

arXiv2017

A Sequential Model for Classifying Temporal Relations between Intra-Sentence Events

We present a sequential model for temporal relation classification between intra-sentence events. The key observation is that the overall syntactic structure and compositional meanings of the multi-word context between events are important for distinguishing among fine-grained temporal relations. Specifically, our approach first extracts a sequence of context words that indicates the temporal relation between two events, which well align with the dependency path between two event mentions. The context word sequence, together with a parts-of-speech tag sequence and a dependency relation sequence that are generated corresponding to the word sequence, are then provided as input to bidirectional recurrent neural network (LSTM) models. The neural nets learn compositional syntactic and semantic representations of contexts surrounding the two events and predict the temporal relation between them. Evaluation of the proposed approach on TimeBank corpus shows that sequential modeling is capable of accurately recognizing temporal relations between events, which outperforms a neural net model using various discrete features as input that imitates previous feature based models.

cs.CL↗

arXiv2017

Event Coreference Resolution by Iteratively Unfolding Inter-dependencies among Events

We introduce a novel iterative approach for event coreference resolution that gradually builds event clusters by exploiting inter-dependencies among event mentions within the same chain as well as across event chains. Among event mentions in the same chain, we distinguish within- and cross-document event coreference links by using two distinct pairwise classifiers, trained separately to capture differences in feature distributions of within- and cross-document event clusters. Our event coreference approach alternates between WD and CD clustering and combines arguments from both event clusters after every merge, continuing till no more merge can be made. And then it performs further merging between event chains that are both closely related to a set of other chains of events. Experiments on the ECB+ corpus show that our model outperforms state-of-the-art methods in joint task of WD and CD event coreference resolution.

cs.CL↗