Previous studies observed that finetuned models may be better base models than the vanilla pretrained model. Such a model, finetuned on some source dataset, may provide a better starting point for a new finetuning process on a desired target dataset. Here, we perform a systematic analysis of this intertraining scheme, over a wide range of English classification tasks. Surprisingly, our analysis suggests that the potential intertraining gain can be analyzed independently for the target dataset under consideration, and for a base model being considered as a starting point. Hence, a performant model is generally strong, even if its training data was not aligned with the target dataset. Furthermore, we leverage our analysis to propose a practical and efficient approach to determine if and how to select a base model in real-world settings. Last, we release an updating ranking of best models in the HuggingFace hub per architecture.

Key Point Analysis (KPA) is an emerging summarization framework, which extracts the main points from a collection of opinions, and quantifies their prevalence. It has been successfully applied to diverse types of data, including arguments, user reviews and survey responses. Despite the growing academic interest in KPA, little attention has been given to the practical challenges of implementing a KPA system in production. This work presents a deployed KPA system, which regularly serves multiple teams in our organization. We discuss the main challenges we faced while building a real-world KPA system, as well as the architecture and algorithmic improvements we developed to address these challenges. Specifically, we focus on efficient matching of sentences to key points, incremental processing, scalability and resiliency. The value of our contributions is demonstrated in an extensive set of experiments, over five existing and novel datasets. Finally, we describe several use cases of the deployed system, which illustrate its practical value.

The COVID-19 pandemic has made a huge global impact and cost millions of lives. As COVID-19 vaccines were rolled out, they were quickly met with widespread hesitancy. To address the concerns of hesitant people, we launched VIRA, a public dialogue system aimed at addressing questions and concerns surrounding the COVID-19 vaccines. Here, we release VIRADialogs, a dataset of over 8k dialogues conducted by actual users with VIRA, providing a unique real-world conversational dataset. In light of rapid changes in users’ intents, due to updates in guidelines or in response to new information, we highlight the important task of intent discovery in this use-case. We introduce a novel automatic evaluation framework for intent discovery, leveraging the existing intent classifier of VIRA. We use this framework to report baseline intent discovery results over VIRADialogs, that highlight the difficulty of this task.

Research on neural networks has focused on understanding a single model trained on a single dataset. However, relatively little is known about the relationships between different models, particularly those trained or tested on different datasets. We address this by studying how the weight space and the underlying loss landscape of different models are interconnected. Specifically, we demonstrate that finetuned models that were optimized for high performance, reside in well-defined regions in weight space, and vice versa – that any model that resides anywhere in those regions also exhibits high performance. Notably, we show that language models that have been finetuned on the same dataset form a tight cluster in the weight space, while models finetuned on different datasets from the same underlying task form a looser cluster. Moreover, traversing around the region between the models leads to new models that perform comparably or even better than models obtained via finetuning, even on tasks that the original models were not finetuned on. Our findings provide insight into the relationships between models, demonstrating that a model positioned between two similar models can acquire the knowledge of both. We leverage this and design a method for selecting a better model for efficient finetuning. Specifically, we show that starting from the center of the region is as effective, if not more, than using the pretrained model in 11 out of 12 datasets, resulting in an average accuracy improvement of 3.06.

Topical Text Classification (TTC) is an ancient, yet timely research area in natural language processing, with many practical applications. The recent dramatic advancements in large LMs raise the question of how well these models can perform in this task in a zero-shot scenario. Here, we share a first comprehensive study, comparing the zero-shot performance of a variety of LMs over TTC23, a large benchmark collection of 23 publicly available TTC datasets, covering a wide range of domains and styles. In addition, we leverage this new TTC benchmark to create LMs that are specialized in TTC, by fine-tuning these LMs over a subset of the datasets and evaluating their performance over the remaining, held-out datasets. We show that the TTC-specialized LMs obtain the top performance on our benchmark, by a significant margin. Our code and model are made available for the community. We hope that the results presented in this work will serve as a useful guide for practitioners interested in topical text classification.

Targeted Sentiment Analysis (TSA) is a central task for generating insights from consumer reviews. Such content is extremely diverse, with sites like Amazon or Yelp containing reviews on products and businesses from many different domains. A real-world TSA system should gracefully handle that diversity. This can be achieved by a multi-domain model – one that is robust to the domain of the analyzed texts, and performs well on various domains. To address this scenario, we present a multi-domain TSA system based on augmenting a given training set with diverse weak labels from assorted domains. These are obtained through self-training on the Yelp reviews corpus. Extensive experiments with our approach on three evaluation datasets across different domains demonstrate the effectiveness of our solution. We further analyze how restrictions imposed on the available labeled data affect the performance, and compare the proposed method to the costly alternative of manually gathering diverse TSA labeled data. Our results and analysis show that our approach is a promising step towards a practical domain-robust TSA system.

Current TSA evaluation in a cross-domain setup is restricted to the small set of review domains available in existing datasets. Such an evaluation is limited, and may not reflect true performance on sites like Amazon or Yelp that host diverse reviews from many domains. To address this gap, we present YASO – a new TSA evaluation dataset of open-domain user reviews. YASO contains 2,215 English sentences from dozens of review domains, annotated with target terms and their sentiment. Our analysis verifies the reliability of these annotations, and explores the characteristics of the collected data. Benchmark results using five contemporary TSA systems show there is ample room for improvement on this challenging new dataset. YASO is available at https://github.com/IBM/yaso-tsa.

Project Debater was revealed in 2019 as the first AI system that can debate human experts on complex topics. Engaging in a live debate requires a diverse set of skills, and Project Debater has been developed accordingly as a collection of components, each designed to perform a specific subtask. Project Debater APIs provide access to many of these capabilities, as well as to more recently developed ones. This diverse set of web services, publicly available for academic use, includes core NLP services, argument mining and analysis capabilities, and higher-level services for content summarization. We describe these APIs and their performance, and demonstrate how they can be used for building practical solutions. In particular, we will focus on Key Point Analysis, a novel technology that identifies the main points and their prevalence in a collection of texts such as survey responses and user reviews.

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. We outline various approaches and discuss the results of the shared task. We expect the task and the findings reported in this paper to be relevant for researchers working on text summarization and argument mining.

Real world scenarios present a challenge for text classification, since labels are usually expensive and the data is often characterized by class imbalance. Active Learning (AL) is a ubiquitous paradigm to cope with data scarcity. Recently, pre-trained NLP models, and BERT in particular, are receiving massive attention due to their outstanding performance in various NLP tasks. However, the use of AL with deep pre-trained models has so far received little consideration. 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. We focus on practical scenarios of binary text classification, where the annotation budget is very small, and the data is often skewed. Our results demonstrate that AL can boost BERT performance, especially in the most realistic scenario in which the initial set of labeled examples is created using keyword-based queries, resulting in a biased sample of the minority class. We release our research framework, aiming to facilitate future research along the lines explored here.

When debating a controversial topic, it is often desirable to expand the boundaries of discussion. For example, we may consider the pros and cons of possible alternatives to the debate topic, make generalizations, or give specific examples. We introduce the task of Debate Topic Expansion - finding such related topics for a given debate topic, along with a novel annotated dataset for the task. We focus on relations between Wikipedia concepts, and show that they differ from well-studied lexical-semantic relations such as hypernyms, hyponyms and antonyms. We present algorithms for finding both consistent and contrastive expansions and demonstrate their effectiveness empirically. We suggest that debate topic expansion may have various use cases in argumentation mining.

Extraction of financial and economic events from text has previously been done mostly using rule-based methods, with more recent works employing machine learning techniques. This work is in line with this latter approach, leveraging relevant Wikipedia sections to extract weak labels for sentences describing economic events. Whereas previous weakly supervised approaches required a knowledge-base of such events, or corresponding financial figures, our approach requires no such additional data, and can be employed to extract economic events related to companies which are not even mentioned in the training data.

The field of Grammatical Error Correction (GEC) has produced various systems to deal with focused phenomena or general text editing. We propose an automatic way to combine black-box systems. Our method automatically detects the strength of a system or the combination of several systems per error type, improving precision and recall while optimizing F-score directly. We show consistent improvement over the best standalone system in all the configurations tested. This approach also outperforms average ensembling of different RNN models with random initializations. In addition, we analyze the use of BERT for GEC - reporting promising results on this end. We also present a spellchecker created for this task which outperforms standard spellcheckers tested on the task of spellchecking. This paper describes a system submission to Building Educational Applications 2019 Shared Task: Grammatical Error Correction. Combining the output of top BEA 2019 shared task systems using our approach, currently holds the highest reported score in the open phase of the BEA 2019 shared task, improving F-0.5 score by 3.7 points over the best result reported.