Search Results for author:
Found 33 papers, 10 papers with code
Using Question Answering Rewards to Improve Abstractive Summarization
Particularly, the results from human evaluations show that the summaries generated by our approach is preferred over 30% of the time over the summaries generated by general abstractive summarization models.
Active Learning for BERT: An Empirical Study
Here, we present a large-scale empirical study on active learning techniques for BERT-based classification, addressing a diverse set of AL strategies and datasets.
TWEETSUMM - A Dialog Summarization Dataset for Customer Service
In most cases, at the end of the conversation, agents are asked to write a short summary emphasizing the problem and the proposed solution, usually for the benefit of other agents that may have to deal with the same customer or issue.
Extractive Summarization
Unsupervised Extractive Summarization
Label Sleuth: From Unlabeled Text to a Classifier in a Few Hours
Text classification can be useful in many real-world scenarios, saving a lot of time for end users.
Quality Controlled Paraphrase Generation
Furthermore, we suggest a method that given a sentence, identifies points in the quality control space that are expected to yield optimal generated paraphrases.
Cluster & Tune: Boost Cold Start Performance in Text Classification
In real-world scenarios, a text classification task often begins with a cold start, when labeled data is scarce.
Fortunately, Discourse Markers Can Enhance Language Models for Sentiment Analysis
In recent years, pretrained language models have revolutionized the NLP world, while achieving state of the art performance in various downstream tasks.
TWEETSUMM -- A Dialog Summarization Dataset for Customer Service
In most cases, at the end of the conversation, agents are asked to write a short summary emphasizing the problem and the proposed solution, usually for the benefit of other agents that may have to deal with the same customer or issue.
Extractive Summarization
Unsupervised Extractive Summarization
Overview of the 2021 Key Point Analysis Shared Task
We describe the 2021 Key Point Analysis (KPA-2021) shared task on key point analysis that we organized as a part of the 8th Workshop on Argument Mining (ArgMining 2021) at EMNLP 2021.
Cluster & Tune: Enhance BERT Performance in Low Resource Text Classification
In such low resources scenarios, we suggest performing an unsupervised classification task prior to fine-tuning on the target task.
YASO: A Targeted Sentiment Analysis Evaluation Dataset for Open-Domain Reviews
Current TSA evaluation in a cross-domain setup is restricted to the small set of review domains available in existing datasets.
Ranked #1 on
Aspect Extraction
on YASO - YELP
Improved Semantic Role Labeling using Parameterized Neighborhood Memory Adaptation
Deep neural models achieve some of the best results for semantic role labeling.
Unsupervised Expressive Rules Provide Explainability and Assist Human Experts Grasping New Domains
Approaching new data can be quite deterrent; you do not know how your categories of interest are realized in it, commonly, there is no labeled data at hand, and the performance of domain adaptation methods is unsatisfactory.
A Survey of the State of Explainable AI for Natural Language Processing
Recent years have seen important advances in the quality of state-of-the-art models, but this has come at the expense of models becoming less interpretable.
Out of the Echo Chamber: Detecting Countering Debate Speeches
An educated and informed consumption of media content has become a challenge in modern times.
A Large-scale Dataset for Argument Quality Ranking: Construction and Analysis
To this end, we created a corpus of 30, 497 arguments carefully annotated for point-wise quality, released as part of this work.
Corpus Wide Argument Mining -- a Working Solution
One of the main tasks in argument mining is the retrieval of argumentative content pertaining to a given topic.
Automatic Argument Quality Assessment - New Datasets and Methods
In spite of the inherent subjective nature of the task, both annotation schemes led to surprisingly consistent results.
Crowd-sourcing annotation of complex NLU tasks: A case study of argumentative content annotation
Recent advancements in machine reading and listening comprehension involve the annotation of long texts.
Automatic Argument Quality Assessment -- New Datasets and Methods
In spite of the inherent subjective nature of the task, both annotation schemes led to surprisingly consistent results.
A Dataset of General-Purpose Rebuttal
In Natural Language Understanding, the task of response generation is usually focused on responses to short texts, such as tweets or a turn in a dialog.
Controversy in Context
With the growing interest in social applications of Natural Language Processing and Computational Argumentation, a natural question is how controversial a given concept is.
Fast End-to-End Wikification
Wikification of large corpora is beneficial for various NLP applications.
Towards Effective Rebuttal: Listening Comprehension using Corpus-Wide Claim Mining
To this end, we collected a large dataset of $400$ speeches in English discussing $200$ controversial topics, mined claims for each topic, and asked annotators to identify the mined claims mentioned in each speech.
Are You Convinced? Choosing the More Convincing Evidence with a Siamese Network
With the advancement in argument detection, we suggest to pay more attention to the challenging task of identifying the more convincing arguments.
From Surrogacy to Adoption; From Bitcoin to Cryptocurrency: Debate Topic Expansion
When debating a controversial topic, it is often desirable to expand the boundaries of discussion.
Listening Comprehension over Argumentative Content
We applied baseline methods addressing the task, to be used as a benchmark for future work over this dataset.
Automatic Speech Recognition (ASR)
Machine Reading Comprehension
+1
Learning Concept Abstractness Using Weak Supervision
We introduce a weakly supervised approach for inferring the property of abstractness of words and expressions in the complete absence of labeled data.
Towards an argumentative content search engine using weak supervision
Our results clearly indicate that the system is able to successfully generalize from the weak signal, outperforming previously reported results in terms of both precision and coverage.
Learning Sentiment Composition from Sentiment Lexicons
Sentiment composition is a fundamental sentiment analysis problem.
Will it Blend? Blending Weak and Strong Labeled Data in a Neural Network for Argumentation Mining
We propose a methodology to blend high quality but scarce strong labeled data with noisy but abundant weak labeled data during the training of neural networks.
Learning Thematic Similarity Metric from Article Sections Using Triplet Networks
We train a triplet network to embed sentences from the same section closer.
Unsupervised corpus--wide claim detection
Automatic claim detection is a fundamental argument mining task that aims to automatically mine claims regarding a topic of consideration.
