BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//project/author//NONSGML v1.0//EN
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTEND:20230403T120000Z
UID:f9065223526cf83ef4e1409c54a221f8-439
DTSTAMP:19700101T120010Z
DESCRIPTION:Inducing Constraints in Paraphrase Generation and Consistency in   Paraphrase Detection
URL;VALUE=URI:https://www.csa.iisc.ac.in/newweb/event/439/inducing-constraints-in-paraphrase-generation-and-consistency-in-paraphrase-detection/
SUMMARY:Deep learning models typically require a large volume of data. Manual   curation of datasets is time-consuming and limited by imagination. As a   result, natural language generation (NLG) has been employed to automate   the process. However, in their vanilla formulation, NLG model are prone   to producing degenerate, uninteresting, and often hallucinated outputs   [58]. Constrained generation aims to overcome these shortcomings by   providing additional information to the generation process. Training   data thus generated can help improve the robustness of deep learning   models. Therefore, the central research question of the thesis is:
<br>
“How can we constrain generation models, especially in NLP, to produce   meaningful outputs and utilize them for building better classification models?”
<br>
To demonstrate how generation models can be constrained, we present two   approaches for paraphrase generation. Paraphrase generation involves  the  generation of text that conveys the same meaning as a reference  text. We  propose two strategies for paraphrase generation:
<br>
1. DiPS (Diversity in Paraphrases using Submodularity): The first   approach deals with constraining paraphrase generation to ensure d=  iversity, i.e., ensuring that generated text(s) are sufficiently  different from each other. We propose a decoding algorithm for   obtaining diverse texts. We provide a novel formulation of the problem   in terms of monotone submodular function maximization, specifically   targeted toward the task of paraphrase generation. We demonstrate the   effectiveness of our method for data augmentation on multiple tasks  such  as intent classification and paraphrase recognition.
<br>
2. SGCP (Syntax Guided Controlled Paraphraser): The second approach   deals with constraining paraphrase generation to ensure syntacticality,   i.e., ensuring that the generated text is syntactically coherent with  an  exemplar sentence. We propose Syntax Guided Controlled Paraphraser   (SGCP), an end-to-end framework for syntactic paraphrase generation   without compromising relevance (fidelity). Through a battery of   automated metrics and comprehensive human evaluation, we verify that   this approach does better than prior works that utilize only limited   syntactic information in the parse tree.
<br>
The second part (meaningful outputs) of the research question pertains   to ensuring that the generated output is meaningful. Towards this, we   present an approach for paraphrase detection to ascertain that the   generated output is semantically coherent with the reference text.   Paraphrase Detection is the task of detecting whether or not the two   input natural language statements are paraphrases of each other.   Fine-tuning pre-trained models such as BERT and RoBERTa on paraphrastic   datasets have become the go-to approaches for such tasks. However,  tasks  like paraphrase detection are symmetric - they require the output  to be  invariant of the order of the inputs. In the traditional  fine-tuned  approach for paraphrase classification, inconsistency is  often observed  in the predicted labels or confidence scores based on  the order of the  inputs. We validate this shortcoming and apply a  consistency loss  function to alleviate inconsistency in symmetric  classification. Our  results show an improved consistency in predictions  for three paraphrase  detection datasets without a significant drop in  the accuracy scores.
<br>
While these works address the research question via paraphrase   generation and detection, the approaches presented here apply broadly  to  NLP-based deep learning models that require imposing constraints and   ensuring consistency. The work on paraphrase generation can be extended   to impose new kinds of constraints (for example, sentiment coherence)  on  generation, while paraphrase detection can be applied to ensure   consistency in other symmetric classification tasks (for example,   sarcasm interpretation) that use deep learning models.
<br>
<br>
Microsoft teams link:
<br>
https://teams.microsoft.com/_#/l/meetup-join/19:meeting_MmIyZTdkYjYtOWFlMy00MTMwLWE4M2ItMDJhZjc1NThkYmQ5@thread.v2/0?context=%7b%22Tid%22%3a%226f15cd97-f6a7-41e3-b2c5-ad4193976476%22%2c%22Oid%22%3a%2258c2a810-9762-463d-90d0-20832b3d1592%22%7d&anon=true&deeplinkId=c94373af-e3bc-4dd5-b297-35c5c191f0f5
DTSTART:20230403T120000Z
END:VEVENT
END:VCALENDAR