Papers by Noam Slonim

Cluster & Tune: Boost Cold Start Performance in Text Classification (2022.acl-long)

Challenge:	Efficient Benchmarking is a method for reducing computation costs of LM evaluation without compromising reliability.
Approach:	They propose to reduce the computation costs of LM evaluation without compromising reliability by using a new measure - Decision Impact on Reliability.
Outcome:	The proposed benchmarks reduce computation costs by x100 or more, while maintaining reliability.

Copied to clipboard

Eyal Shnarch, Ariel Gera, Alon Halfon, Lena Dankin, Leshem Choshen, Ranit Aharonov, Noam Slonim

Automatic Argument Quality Assessment - New Datasets and Methods (D19-1)

Challenge:	Existing methods to fine-tune pre-trained models for text classification are poor in practice.
Approach:	They propose to add an intermediate unsupervised classification task between pre-training and fine-tuning phases to boost performance of pre-trained models.
Outcome:	The proposed method improves performance on topical classification tasks when labeled data is scarce.

Copied to clipboard

Assaf Toledo, Shai Gretz, Edo Cohen-Karlik, Roni Friedman, Elad Venezian, Dan Lahav, Michal Jacovi, Ranit Aharonov, Noam Slonim

Challenge:	6.3k arguments were collected from contributors of various levels, and are released as part of this work.
Approach:	They propose to use a language model to annotate arguments for argument ranking and argument-pair classification.
Outcome:	The proposed methods outperform state-of-the-art methods in the argument ranking task and argument-pair classification task.

From Surrogacy to Adoption; From Bitcoin to Cryptocurrency: Debate Topic Expansion (P19-1)

Copied to clipboard

Roy Bar-Haim, Dalia Krieger, Orith Toledo-Ronen, Lilach Edelstein, Yonatan Bilu, Alon Halfon, Yoav Katz, Amir Menczel, Ranit Aharonov, Noam Slonim

From Arguments to Key Points: Towards Automatic Argument Summarization (2020.acl-main)

Challenge:	Recent advances in argumentation mining have left much of the relevant argumentative content out of reach.
Approach:	They propose a task of Debate Topic Expansion to find related topics for a given debate topic, along with an annotated dataset for the task.
Outcome:	The proposed algorithms differ from well-studied lexical-semantic relations and show they work well in argumentation mining.

Copied to clipboard

Roy Bar-Haim, Lilach Eden, Roni Friedman, Yoav Kantor, Dan Lahav, Noam Slonim

Text Generation

Challenge:	Recent work on topic-related argument mining has made it difficult to read and digest large amounts of information.
Approach:	They propose to represent arguments as a small set of talking points, termed key points, each scored according to its salience.
Outcome:	The proposed method can predict key points in advance, and it performs well.

Welcome to the Real World: Efficient, Incremental and Scalable Key Point Analysis (2023.emnlp-industry)

Copied to clipboard

Lilach Eden, Yoav Kantor, Matan Orbach, Yoav Katz, Noam Slonim, Roy Bar-Haim

Green & Sustainable NLP

Challenge:	Key Point Analysis (KPA) extracts the main points from opinions and quantifies their prevalence.
Approach:	They propose a key point analysis framework that extracts the main points from opinions and quantifies their prevalence.
Outcome:	The proposed system is able to match sentences to key points over five datasets and demonstrate its performance.

Knowledge is a Region in Weight Space for Fine-tuned Language Models (2023.findings-emnlp)

Copied to clipboard

Almog Gueta, Elad Venezian, Colin Raffel, Noam Slonim, Yoav Katz, Leshem Choshen

Quantitative argument summarization and beyond: Cross-domain key point analysis (2020.emnlp-main)

Challenge:	Specifically, language models that have been finetuned on the same dataset form a tight cluster in the weight space, while models finetuning on different datasets from the same underlying task form s looser clusters.
Approach:	They analyze the weight space and the underlying loss landscape of different models to determine how they are interconnected and how they perform.
Outcome:	The proposed method improves accuracy on 11 out of 12 datasets by starting from the center of the region, if not more, than using the pretrained model.

Copied to clipboard

Roy Bar-Haim, Yoav Kantor, Lilach Eden, Roni Friedman, Dan Lahav, Noam Slonim

Text Generation

Challenge:	Recent work on multi-document summarization lacks quantitative aspect of summarizing views, arguments or opinions . authors develop method for automatic extraction of key points, which is comparable to a human expert .
Approach:	They propose to map arguments to a small set of expert-generated key points . they demonstrate that the applicability of key point analysis goes well beyond argumentation data .
Outcome:	The proposed method outperforms arguments in municipal surveys and user reviews . it is shown that the extraction of key points is comparable to a human expert .

A Dataset of General-Purpose Rebuttal (D19-1)

Copied to clipboard

Matan Orbach, Yonatan Bilu, Ariel Gera, Yoav Kantor, Lena Dankin, Tamar Lavee, Lili Kotlerman, Shachar Mirkin, Michal Jacovi, Ranit Aharonov, Noam Slonim

Multimodality

Challenge:	a key element in argumentation is rebuttal, the ability to contest an argument by presenting a counter-argument.
Approach:	They propose a method based on general rebuttal arguments to produce a critical response to a long argumentative text.
Outcome:	The proposed method overcomes the need for topic-specific arguments to be provided . it allows creating responses beyond the scope of topics for which specific arguments are available .

Learning Thematic Similarity Metric from Article Sections Using Triplet Networks (P18-2)

Copied to clipboard

Liat Ein Dor, Yosi Mass, Alon Halfon, Elad Venezian, Ilya Shnayderman, Ranit Aharonov, Noam Slonim

Financial Event Extraction Using Wikipedia-Based Weak Supervision (D19-51)

Challenge:	In this paper, we use Wikipedia articles to learn thematic similarity metric between sentences.
Approach:	They propose to leverage the partition of articles into sections to learn thematic similarity metric between sentences.
Outcome:	The proposed model outperforms state-of-the-art embeddings on the task of thematic clustering of sentences.

Copied to clipboard

Liat Ein-Dor, Ariel Gera, Orith Toledo-Ronen, Alon Halfon, Benjamin Sznajder, Lena Dankin, Yonatan Bilu, Yoav Katz, Noam Slonim

Listening Comprehension over Argumentative Content (D18-1)

Challenge:	Existing methods for detecting financial and economic events from text have relied on a knowledge-base of financial events, or corresponding financial figures.
Approach:	They propose to use Wikipedia sections to extract weak labels for sentences describing economic events from text.
Outcome:	The proposed method can extract weak labels for sentences describing economic events from Wikipedia sentences.

Copied to clipboard

Shachar Mirkin, Guy Moshkowich, Matan Orbach, Lili Kotlerman, Yoav Kantor, Tamar Lavee, Michal Jacovi, Yonatan Bilu, Ranit Aharonov, Noam Slonim

Speech & Audio in NLP

Challenge:	In argumentation domain, people are exposed directly to audio (or the video), without access to a written version.
Approach:	They present a task for machine listening comprehension in the argumentation domain and a dataset in English.
Outcome:	The proposed task is based on 200 speeches arguing for or against 50 controversial topics and uses baseline methods to address it.

Efficient Methods for Natural Language Processing: A Survey (2023.tacl-1)

Copied to clipboard

Marcos Treviso, Ji-Ung Lee, Tianchu Ji, Betty van Aken, Qingqing Cao, Manuel R. Ciosici, Michael Hassid, Kenneth Heafield, Sara Hooker, Colin Raffel, Pedro H. Martins, André F. T. Martins, Jessica Zosa Forde, Peter Milder, Edwin Simpson, Noam Slonim, Jesse Dodge, Emma Strubell, Niranjan Balasubramanian, Leon Derczynski, Iryna Gurevych, Roy Schwartz

Green & Sustainable NLP

Challenge:	Recent work in natural language processing (NLP) has yielded appealing results from scaling model parameters and training data, but using only scale to improve performance means resource consumption also grows.
Approach:	They propose to use data, time, storage, or energy to improve model performance.
Outcome:	The proposed methods and findings provide guidance for conducting NLP under limited resources and point towards promising research directions for developing more efficient methods.

Zero-shot Topical Text Classification with LLMs - an Experimental Study (2023.findings-emnlp)

Copied to clipboard

Shai Gretz, Alon Halfon, Ilya Shnayderman, Orith Toledo-Ronen, Artem Spector, Lena Dankin, Yannis Katsis, Ofir Arviv, Yoav Katz, Noam Slonim, Liat Ein-Dor

Liat Ein Dor, Alon Halfon, Yoav Kantor, Ran Levy, Yosi Mass, Ruty Rinott, Eyal Shnarch, Noam Slonim

Challenge:	Topical text classification is an ancient, yet timely research area in natural language processing.
Approach:	They compare the zero-shot performance of a variety of LMs over a large dataset of 23 publicly available TTC datasets.
Outcome:	The proposed models outperform their counterparts over a large dataset and show that they perform better in a zero-shot scenario.

Copied to clipboard

Challenge:	Existing methods to measure relatedness between Wikipedia concepts are lacking.
Approach:	They propose a new type of concept relatedness dataset, WORD, which is annotated by a human . they use this dataset to assess relatedness between Wikipedia concepts using supervised methods.
Outcome:	The proposed dataset outperforms existing methods for measuring relatedness between Wikipedia concepts.

Advances in Debating Technologies: Building AI That Can Debate Humans (2021.acl-tutorials)

Copied to clipboard

Roy Bar-Haim, Liat Ein-Dor, Matan Orbach, Elad Venezian, Noam Slonim

Argument Mining

Challenge:	This tutorial focuses on Debating Technologies, a sub-field of computational argumentation defined as "computational technologies developed directly to enhance, support, and engage with human debating" the tutorial provides a holistic view of a debated system, and discusses practical applications and future challenges of debation technologies.
Approach:	They present a tutorial on Debating Technologies, a sub-field of computational argumentation . they introduce Project Debater, which is the first AI system to debate human experts .
Outcome:	The project Debater is the first AI system to debate human experts on complex topics.

Multilingual Argument Mining: Datasets and Analysis (2020.findings-emnlp)

Copied to clipboard

Orith Toledo-Ronen, Matan Orbach, Yonatan Bilu, Artem Spector, Noam Slonim

Multilinguality

Challenge:	Argument mining tasks in non-English languages are dominated by English . we use a pre-trained language model that supports 104 languages to train models .
Approach:	They propose a multilingual BERT model to address argument mining tasks in non-English languages . they use English datasets and machine translation to facilitate transfer learning .
Outcome:	The proposed model is well suited for classifying the stance of arguments and detecting evidence, but less so for assessing the quality of arguments.

ColD Fusion: Collaborative Descent for Distributed Multitask Finetuning (2023.acl-long)

Copied to clipboard

Shachar Don-Yehiya, Elad Venezian, Colin Raffel, Noam Slonim, Leshem Choshen

Towards an argumentative content search engine using weak supervision (C18-1)

Challenge:	Pretraining has been shown to scale well with compute, data size and data diversity.
Approach:	They propose a method that provides benefits of multitask learning but leverages distributed computation . they propose 'coldfusion' can create synergistic loop where finetuned models can be "recycled"
Outcome:	The proposed method outperforms RoBERTa and previous multitask models on 35 datasets.

Copied to clipboard

Ran Levy, Ben Bogin, Shai Gretz, Ranit Aharonov, Noam Slonim

Responsible & Trustworthy NLP

Challenge:	Existing work focused on detecting claims within a small set of documents . however, pinpointing relevant claims within massive unstructured corpora, received little attention.
Approach:	They propose to use a weak signal to develop a query for claim–sentence detection using a large text corpus.
Outcome:	The proposed system outperforms previous results in terms of precision and coverage.

Argument Invention from First Principles (P19-1)

Copied to clipboard

Yonatan Bilu, Ariel Gera, Daniel Hershcovich, Benjamin Sznajder, Dan Lahav, Guy Moshkowich, Anael Malet, Assaf Gavron, Noam Slonim

Multi-Domain Targeted Sentiment Analysis (2022.naacl-main)

Challenge:	Argument Invention is a task that is often referred to as a natural way of inventing arguments, but has not been formalized in the context of NLP.
Approach:	They propose to define a taxonomy of recurring arguments and to automatically identify which of them are relevant to the topic.
Outcome:	The proposed taxonomy is coherent, covers the relevant topics and coincides with what debaters actually argue in their speeches, and facilitates automatic argument invention for new topics.

Copied to clipboard

Orith Toledo-Ronen, Matan Orbach, Yoav Katz, Noam Slonim

Robustness in NLP

Challenge:	Targeted Sentiment Analysis (TSA) is a task for generating insights from consumer reviews.
Approach:	They propose a multi-domain TSA system that augments a given training set with diverse weak labels from assorted domains and augments it with Yelp reviews.
Outcome:	The proposed model outperforms manual methods on three evaluation datasets across different domains and shows that it performs well.

Active Learning for Natural Language Generation (2023.emnlp-main)

Copied to clipboard

Yotam Perlitz, Ariel Gera, Michal Shmueli-Scheuer, Dafna Sheinwald, Noam Slonim, Liat Ein-Dor

Zero-Shot Text Classification with Self-Training (2022.emnlp-main)

Challenge:	Existing approaches to NLG are limited by the lack of annotated data.
Approach:	They propose to use active learning to reduce the cost of manual annotation to improve annotation efficiency by selecting the most informative examples to label.
Outcome:	The proposed approach surpasses baseline of random example selection in some cases but not in others.

Copied to clipboard

Ariel Gera, Alon Halfon, Eyal Shnarch, Yotam Perlitz, Liat Ein-Dor, Noam Slonim

Will it Blend? Blending Weak and Strong Labeled Data in a Neural Network for Argumentation Mining (P18-2)

Challenge:	Recent advances in large pretrained language models have increased attention to zero-shot text classification.
Approach:	They propose a plug-and-play method to bridge this gap by requiring only class names along with an unlabeled dataset.
Outcome:	The proposed model can be trained on a natural language inference dataset and performs on dozens of unseen tasks without the need for domain expertise or trial and error.

Copied to clipboard

Eyal Shnarch, Carlos Alzate, Lena Dankin, Martin Gleize, Yufang Hou, Leshem Choshen, Ranit Aharonov, Noam Slonim

Benchmark Data and Evaluation Framework for Intent Discovery Around COVID-19 Vaccine Hesitancy (2023.findings-eacl)

Challenge:	Obtaining high quality labeled data for natural language understanding tasks is slow, error-prone, complicated and expensive.
Approach:	They propose a method to blend weak and strong labeled data during the training of neural networks using a topic-dependent evidence detection dataset.
Outcome:	The proposed method improves the training of neural networks when a small amount of labeled data is available.

Copied to clipboard

Shai Gretz, Assaf Toledo, Roni Friedman, Dan Lahav, Rose Weeks, Naor Bar-Zeev, João Sedoc, Pooja Sangha, Yoav Katz, Noam Slonim

Natural Language Interfaces

Challenge:	As COVID-19 vaccines were rolled out, they were met with widespread hesitancy.
Approach:	They propose a new framework for intent discovery that leverages existing intent classifiers to provide a real-world conversational dataset of conversations conducted by actual users with VIRA.
Outcome:	The proposed framework enables users to find out what they are doing and why they are hesitant.

The Benefits of Bad Advice: Autocontrastive Decoding across Model Layers (2023.acl-long)

Copied to clipboard

Ariel Gera, Roni Friedman, Ofir Arviv, Chulaka Gunasekara, Benjamin Sznajder, Noam Slonim, Eyal Shnarch

The workweek is the best time to start a family – A Study of GPT-2 Based Claim Generation (2020.findings-emnlp)

Challenge:	Existing approaches to apply language models to tasks that require intermediate representations are less informative.
Approach:	They propose a novel approach that utilizes the contrast between layers to improve text generation outputs.
Outcome:	The proposed approach mitigates degenerative behaviors of the model in open-ended generation, significantly improving the quality of generated texts.

Copied to clipboard

Shai Gretz, Yonatan Bilu, Edo Cohen-Karlik, Noam Slonim

Crowd-sourcing annotation of complex NLU tasks: A case study of argumentative content annotation (D19-59)

Challenge:	Argument generation is a challenging task whose impact on social media is growing . we examine how argument generation can be enhanced to provide better arguments .
Approach:	They propose a pipeline for argument generation based on GPT-2 . they examine the types of claims it produces, and their veracity .
Outcome:	The proposed pipeline improves argument generation quality and provides a clear stance on a debate topic.

Copied to clipboard

Tamar Lavee, Lili Kotlerman, Matan Orbach, Yonatan Bilu, Michal Jacovi, Ranit Aharonov, Noam Slonim

Challenge:	Recent advances in machine reading and listening comprehension involve the annotation of long texts.
Approach:	They propose a way to perform a sentence-by-sentence annotation task with crowd annotators.
Outcome:	The proposed approach can be used to identify claims in a debate speech.

A Recorded Debating Dataset (L18-1)

Copied to clipboard

Shachar Mirkin, Michal Jacovi, Tamar Lavee, Hong-Kwang Kuo, Samuel Thomas, Leslie Sager, Lili Kotlerman, Elad Venezian, Noam Slonim

Multimodality

Challenge:	Existing research in computational argumentation and debating technologies focuses on argumentation mining, but other tasks are being addressed as well.
Approach:	They describe a dataset of debating speeches in English that is used for research . they use an automatic speech recognition system to produce a more "nLP-friendly" text .
Outcome:	The proposed dataset contains 60 speeches on various controversial topics, each in five formats corresponding to different stages in production.

Learning Sentiment Composition from Sentiment Lexicons (C18-1)

Copied to clipboard

Orith Toledo-Ronen, Roy Bar-Haim, Alon Halfon, Charles Jochim, Amir Menczel, Ranit Aharonov, Noam Slonim

Sentiment Analysis

Challenge:	Sentiment composition is a fundamental problem in sentiment analysis.
Approach:	They propose a method for learning sentiment composition from a large, unlabeled corpus . they automatically generate large sentiment lexicons of bigrams and unigrams .
Outcome:	The proposed approach is validated through manual annotation and sentiment classification experiments with phrase-level and sentence-level benchmarks.

Where to start? Analyzing the potential value of intermediate models (2023.emnlp-main)

Copied to clipboard

Leshem Choshen, Elad Venezian, Shachar Don-Yehiya, Noam Slonim, Yoav Katz

YASO: A Targeted Sentiment Analysis Evaluation Dataset for Open-Domain Reviews (2021.emnlp-main)

Challenge:	a finetuned model may be better base models than the vanilla pretrained model . this scheme, often referred to as intertraining, is the focus of the present work .
Approach:	They propose a scheme to analyze the potential intertraining gain independently for the target dataset and for a base model being considered as a starting point.
Outcome:	The proposed model is strong even if training data was not aligned with target dataset.

Copied to clipboard

Matan Orbach, Orith Toledo-Ronen, Artem Spector, Ranit Aharonov, Yoav Katz, Noam Slonim

Sentiment Analysis

Challenge:	YASO contains 2,215 English sentences from dozens of review domains, annotated with target terms and their sentiment.
Approach:	They propose a new TSA evaluation dataset of open-domain user reviews in English . YASO contains 2,215 English sentences annotated with target terms and their sentiment .
Outcome:	The proposed dataset verifies the reliability of the annotations and explores the characteristics of the collected data.

Project Debater APIs: Decomposing the AI Grand Challenge (2021.emnlp-demo)

Copied to clipboard

Roy Bar-Haim, Yoav Kantor, Elad Venezian, Yoav Katz, Noam Slonim

Challenge:	Project Debater is the first AI system that can debate human experts on complex topics.
Approach:	They describe Project Debater's architecture and evaluate its performance . they will focus on Key Point Analysis, a novel technology that identifies main points .
Outcome:	The proposed system can debate human experts on complex topics.

Are You Convinced? Choosing the More Convincing Evidence with a Siamese Network (P19-1)

Copied to clipboard

Martin Gleize, Eyal Shnarch, Leshem Choshen, Lena Dankin, Guy Moshkowich, Ranit Aharonov, Noam Slonim

Out of the Echo Chamber: Detecting Countering Debate Speeches (2020.acl-main)

Challenge:	Recent advances in argument detection have made it easier to identify the more convincing arguments.
Approach:	They propose a new data set of pairs of evidence labeled for convincingness that is more challenging than existing alternatives.
Outcome:	The proposed method outperforms baselines on convincingness data and its own.

Copied to clipboard

Matan Orbach, Yonatan Bilu, Assaf Toledo, Dan Lahav, Michal Jacovi, Ranit Aharonov, Noam Slonim

Multimodality

Challenge:	Existing algorithms to detect articles that counter the arguments in debate speeches are unsuccessful, suggesting room for further research.
Approach:	They propose a task to detect articles that counter the arguments made in debate speeches by annotating them from a dataset of 3,685 such speeches.
Outcome:	The proposed algorithm can detect articles that counter the arguments made in debate speeches, and some are successful, but none are human-like.

Active Learning for BERT: An Empirical Study (2020.emnlp-main)

Copied to clipboard

Liat Ein-Dor, Alon Halfon, Ariel Gera, Eyal Shnarch, Lena Dankin, Leshem Choshen, Marina Danilevsky, Ranit Aharonov, Yoav Katz, Noam Slonim

Unsupervised Expressive Rules Provide Explainability and Assist Human Experts Grasping New Domains (2020.findings-emnlp)

Challenge:	Existing approaches to deal with data scarcity are active learning (AL) and pre-trained models are not being considered.
Approach:	They propose to use active learning techniques to cope with data scarcity in binary text classification scenarios where the annotation budget is very small and the data is often skewed.
Outcome:	The proposed methods improve BERT performance in binary text classification scenarios where the annotation budget is very small and the data is often skewed.

Copied to clipboard

Eyal Shnarch, Leshem Choshen, Guy Moshkowich, Ranit Aharonov, Noam Slonim

Responsible & Trustworthy NLP

Challenge:	Understanding unexplored data is a slow process, and there is no labeled data at hand.
Approach:	They propose to use unsupervised methods to reveal rules which cluster unexplored corpus by its prominent categories to help domain experts understand their texts.
Outcome:	The proposed rules can be bootstrapped to identify target categories and deepen understanding of the data.

Every Bite Is an Experience: Key Point Analysis of Business Reviews (2021.acl-long)

Copied to clipboard

Roy Bar-Haim, Lilach Eden, Yoav Kantor, Roni Friedman, Noam Slonim