Given the success of Transformer-based models, two directions of study have emerged: interpreting role of individual attention heads and down-sizing the models for efficiency. Our work straddles these two streams: We analyse the importance of basing pruning strategies on the interpreted role of the attention heads. We evaluate this on Transformer and BERT models on multiple NLP tasks. Firstly, we find that a large fraction of the attention heads can be randomly pruned with limited effect on accuracy. Secondly, for Transformers, we find no advantage in pruning attention heads identified to be important based on existing studies that relate importance to the location of a head. On the BERT model too we find no preference for top or bottom layers, though the latter are reported to have higher importance. However, strategies that avoid pruning middle layers and consecutive layers perform better. Finally, during fine-tuning the compensation for pruned attention heads is roughly equally distributed across the un-pruned heads. Our results thus suggest that interpretation of attention heads does not strongly inform pruning.

BERT and its variants have achieved state-of-the-art performance in various NLP tasks. Since then, various works have been proposed to analyze the linguistic information being captured in BERT. However, the current works do not provide an insight into how BERT is able to achieve near human-level performance on the task of Reading Comprehension based Question Answering. In this work, we attempt to interpret BERT for RCQA. Since BERT layers do not have predefined roles, we define a layer’s role or functionality using Integrated Gradients. Based on the defined roles, we perform a preliminary analysis across all layers. We observed that the initial layers focus on query-passage interaction, whereas later layers focus more on contextual understanding and enhancing the answer prediction. Specifically for quantifier questions (how much/how many), we notice that BERT focuses on confusing words (i.e., on other numerical quantities in the passage) in the later layers, but still manages to predict the answer correctly. The fine-tuning and analysis scripts will be publicly available at https://github.com/iitmnlp/BERT-Analysis-RCQA.

Recent studies on interpretability of attention distributions have led to notions of faithful and plausible explanations for a model’s predictions. Attention distributions can be considered a faithful explanation if a higher attention weight implies a greater impact on the model’s prediction. They can be considered a plausible explanation if they provide a human-understandable justification for the model’s predictions. In this work, we first explain why current attention mechanisms in LSTM based encoders can neither provide a faithful nor a plausible explanation of the model’s predictions. We observe that in LSTM based encoders the hidden representations at different time-steps are very similar to each other (high conicity) and attention weights in these situations do not carry much meaning because even a random permutation of the attention weights does not affect the model’s predictions. Based on experiments on a wide variety of tasks and datasets, we observe attention distributions often attribute the model’s predictions to unimportant words such as punctuation and fail to offer a plausible explanation for the predictions. To make attention mechanisms more faithful and plausible, we propose a modified LSTM cell with a diversity-driven training objective that ensures that the hidden representations learned at different time steps are diverse. We show that the resulting attention distributions offer more transparency as they (i) provide a more precise importance ranking of the hidden states (ii) are better indicative of words important for the model’s predictions (iii) correlate better with gradient-based attribution methods. Human evaluations indicate that the attention distributions learned by our model offer a plausible explanation of the model’s predictions. Our code has been made publicly available at https://github.com/akashkm99/Interpretable-Attention

In this work, we focus on the task of Automatic Question Generation (AQG) where given a passage and an answer the task is to generate the corresponding question. It is desired that the generated question should be (i) grammatically correct (ii) answerable from the passage and (iii) specific to the given answer. An analysis of existing AQG models shows that they produce questions which do not adhere to one or more of the above-mentioned qualities. In particular, the generated questions look like an incomplete draft of the desired question with a clear scope for refinement. To alleviate this shortcoming, we propose a method which tries to mimic the human process of generating questions by first creating an initial draft and then refining it. More specifically, we propose Refine Network (RefNet) which contains two decoders. The second decoder uses a dual attention network which pays attention to both (i) the original passage and (ii) the question (initial draft) generated by the first decoder. In effect, it refines the question generated by the first decoder, thereby making it more correct and complete. We evaluate RefNet on three datasets, viz., SQuAD, HOTPOT-QA, and DROP, and show that it outperforms existing state-of-the-art methods by 7-16% on all of these datasets. Lastly, we show that we can improve the quality of the second decoder on specific metrics, such as, fluency and answerability by explicitly rewarding revisions that improve on the corresponding metric during training. The code has been made publicly available .

There has always been criticism for using n-gram based similarity metrics, such as BLEU, NIST, etc, for evaluating the performance of NLG systems. However, these metrics continue to remain popular and are recently being used for evaluating the performance of systems which automatically generate questions from documents, knowledge graphs, images, etc. Given the rising interest in such automatic question generation (AQG) systems, it is important to objectively examine whether these metrics are suitable for this task. In particular, it is important to verify whether such metrics used for evaluating AQG systems focus on answerability of the generated question by preferring questions which contain all relevant information such as question type (Wh-types), entities, relations, etc. In this work, we show that current automatic evaluation metrics based on n-gram similarity do not always correlate well with human judgments about answerability of a question. To alleviate this problem and as a first step towards better evaluation metrics for AQG, we introduce a scoring function to capture answerability and show that when this scoring function is integrated with existing metrics, they correlate significantly better with human judgments. The scripts and data developed as a part of this work are made publicly available.

In this work, we focus on the task of generating natural language descriptions from a structured table of facts containing fields (such as nationality, occupation, etc) and values (such as Indian, actor, director, etc). One simple choice is to treat the table as a sequence of fields and values and then use a standard seq2seq model for this task. However, such a model is too generic and does not exploit task specific characteristics. For example, while generating descriptions from a table, a human would attend to information at two levels: (i) the fields (macro level) and (ii) the values within the field (micro level). Further, a human would continue attending to a field for a few timesteps till all the information from that field has been rendered and then never return back to this field (because there is nothing left to say about it). To capture this behavior we use (i) a fused bifocal attention mechanism which exploits and combines this micro and macro level information and (ii) a gated orthogonalization mechanism which tries to ensure that a field is remembered for a few time steps and then forgotten. We experiment with a recently released dataset which contains fact tables about people and their corresponding one line biographical descriptions in English. In addition, we also introduce two similar datasets for French and German. Our experiments show that the proposed model gives 21% relative improvement over a recently proposed state of the art method and 10% relative improvement over basic seq2seq models. The code and the datasets developed as a part of this work are publicly available on https://github.com/PrekshaNema25/StructuredData_To_Descriptions

Structured data summarization involves generation of natural language summaries from structured input data. In this work, we consider summarizing structured data occurring in the form of tables as they are prevalent across a wide variety of domains. We formulate the standard table summarization problem, which deals with tables conforming to a single predefined schema. To this end, we propose a mixed hierarchical attention based encoder-decoder model which is able to leverage the structure in addition to the content of the tables. Our experiments on the publicly available weathergov dataset show around 18 BLEU (around 30%) improvement over the current state-of-the-art.

Abstractive summarization aims to generate a shorter version of the document covering all the salient points in a compact and coherent fashion. On the other hand, query-based summarization highlights those points that are relevant in the context of a given query. The encode-attend-decode paradigm has achieved notable success in machine translation, extractive summarization, dialog systems, etc. But it suffers from the drawback of generation of repeated phrases. In this work we propose a model for the query-based summarization task based on the encode-attend-decode paradigm with two key additions (i) a query attention model (in addition to document attention model) which learns to focus on different portions of the query at different time steps (instead of using a static representation for the query) and (ii) a new diversity based attention model which aims to alleviate the problem of repeating phrases in the summary. In order to enable the testing of this model we introduce a new query-based summarization dataset building on debatepedia. Our experiments show that with these two additions the proposed model clearly outperforms vanilla encode-attend-decode models with a gain of 28% (absolute) in ROUGE-L scores.