Amir Globerson


pdf bib
Crawling The Internal Knowledge-Base of Language Models
Roi Cohen | Mor Geva | Jonathan Berant | Amir Globerson
Findings of the Association for Computational Linguistics: EACL 2023

Language models are trained on large volumes of text, and as a result their parameters might contain a significant body of factual knowledge. Any downstream task performed by these models implicitly builds on these facts, and thus it is highly desirable to have means for representing this body of knowledge in an interpretable way. However, there is currently no mechanism for such a representation. Here, we propose to address this goal by extracting a knowledge-graph of facts from a given language model. We describe a procedure for “crawling” the internal knowledge-base of a language model. Specifically, given a seed entity, we expand a knowledge-graph around it. The crawling procedure is decomposed into sub-tasks, realized through specially designed prompts that control for both precision (i.e., that no wrong facts are generated) and recall (i.e., the number of facts generated). We evaluate our approach on graphs crawled starting from dozens of seed entities, and show it yields high precision graphs (82-92%), while emitting a reasonable number of facts per entity.

pdf bib
In-Context Learning Creates Task Vectors
Roee Hendel | Mor Geva | Amir Globerson
Findings of the Association for Computational Linguistics: EMNLP 2023

In-context learning (ICL) in Large Language Models (LLMs) has emerged as a powerful new learning paradigm. However, its underlying mechanism is still not well understood. In particular, it is challenging to map it to the “standard’ machine learning framework, where one uses a training set S to find a best-fitting function f(x) in some hypothesis class. Here we make progress on this problem by showing that the functions learned by ICL often have a very simple structure: they correspond to the transformer LLM whose only inputs are the query x and a single “task vector’ calculated from the training set. Thus, ICL can be seen as compressing S into a single task vector 𝜃(S) and then using this task vector to modulate the transformer to produce the output. We support the above claim via comprehensive experiments across a range of models and tasks.

pdf bib
Dissecting Recall of Factual Associations in Auto-Regressive Language Models
Mor Geva | Jasmijn Bastings | Katja Filippova | Amir Globerson
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Transformer-based language models (LMs) are known to capture factual knowledge in their parameters. While previous work looked into where factual associations are stored, only little is known about how they are retrieved internally during inference. We investigate this question through the lens of information flow. Given a subject-relation query, we study how the model aggregates information about the subject and relation to predict the correct attribute. With interventions on attention edges, we first identify two critical points where information propagates to the prediction: one from the relation positions followed by another from the subject positions. Next, by analyzing the information at these points, we unveil a three-step internal mechanism for attribute extraction. First, the representation at the last-subject position goes through an enrichment process, driven by the early MLP sublayers, to encode many subject-related attributes. Second, information from the relation propagates to the prediction. Third, the prediction representation “queries” the enriched subject to extract the attribute. Perhaps surprisingly, this extraction is typically done via attention heads, which often encode subject-attribute mappings in their parameters. Overall, our findings introduce a comprehensive view of how factual associations are stored and extracted internally in LMs, facilitating future research on knowledge localization and editing.

pdf bib
LM vs LM: Detecting Factual Errors via Cross Examination
Roi Cohen | May Hamri | Mor Geva | Amir Globerson
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

A prominent weakness of modern language models (LMs) is their tendency to generate factually incorrect text, which hinders their usability. A natural question is whether such factual errors can be detected automatically. Inspired by truth-seeking mechanisms in law, we propose a factuality evaluation framework for LMs that is based on cross-examination. Our key idea is that an incorrect claim is likely to result in inconsistency with other claims that the model generates. To discover such inconsistencies, we facilitate a multi-turn interaction between the LM that generated the claim and another LM (acting as an examiner) which introduces questions to discover inconsistencies. We empirically evaluate our method on factual claims made by multiple recent LMs on four benchmarks, finding that it outperforms existing methods and baselines, often by a large gap. Our results demonstrate the potential of using interacting LMs for capturing factual errors.

pdf bib
Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs
Roei Herzig | Alon Mendelson | Leonid Karlinsky | Assaf Arbelle | Rogerio Feris | Trevor Darrell | Amir Globerson
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Vision and language models (VLMs) have demonstrated remarkable zero-shot (ZS) performance in a variety of tasks. However, recent works have shown that even the best VLMs struggle to capture aspects of compositional scene understanding, such as object attributes, relations, and action states. In contrast, obtaining structured annotations, such as scene graphs (SGs), that could improve these models is time-consuming and costly, and thus cannot be used on a large scale. Here we ask whether small SG datasets can provide sufficient information for enhancing structured understanding of pretrained VLMs. We show that it is indeed possible to improve VLMs when learning from SGs by integrating components that incorporate structured information into both visual and textual representations. For the visual side, we incorporate a special “SG Component” in the image transformer trained to predict SG information, while for the textual side, we utilize SGs to generate fine-grained captions that highlight different compositional aspects of the scene. Our method improves the performance of several popular VLMs on multiple VL datasets with only a mild degradation in ZS capabilities.

pdf bib
What Are You Token About? Dense Retrieval as Distributions Over the Vocabulary
Ori Ram | Liat Bezalel | Adi Zicher | Yonatan Belinkov | Jonathan Berant | Amir Globerson
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Dual encoders are now the dominant architecture for dense retrieval. Yet, we have little understanding of how they represent text, and why this leads to good performance. In this work, we shed light on this question via distributions over the vocabulary. We propose to interpret the vector representations produced by dual encoders by projecting them into the model’s vocabulary space. We show that the resulting projections contain rich semantic information, and draw connection between them and sparse retrieval. We find that this view can offer an explanation for some of the failure cases of dense retrievers. For example, we observe that the inability of models to handle tail entities is correlated with a tendency of the token distributions to forget some of the tokens of those entities. We leverage this insight and propose a simple way to enrich query and passage representations with lexical information at inference time, and show that this significantly improves performance compared to the original model in zero-shot settings, and specifically on the BEIR benchmark.

pdf bib
Covering Uncommon Ground: Gap-Focused Question Generation for Answer Assessment
Roni Rabin | Alexandre Djerbetian | Roee Engelberg | Lidan Hackmon | Gal Elidan | Reut Tsarfaty | Amir Globerson
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

Human communication often involves information gaps between the interlocutors. For example, in an educational dialogue a student often provides an answer that is incomplete, and there is a gap between this answer and the perfect one expected by the teacher. Successful dialogue then hinges on the teacher asking about this gap in an effective manner, thus creating a rich and interactive educational experience. We focus on the problem of generating such gap-focused questions (GFQs) automatically. We define the task, highlight key desired aspects of a good GFQ, and propose a model that satisfies these. Finally, we provide an evaluation by human annotators of our generated questions compared against human generated ones, demonstrating competitive performance.


pdf bib
Text-Only Training for Image Captioning using Noise-Injected CLIP
David Nukrai | Ron Mokady | Amir Globerson
Findings of the Association for Computational Linguistics: EMNLP 2022

We consider the task of image-captioning using only the CLIP model and additional text data at training time and no additional captioned images. Our approach relies on the fact that CLIP is trained to make visual and textual embeddings similar. Therefore, we only need to learn how to translate CLIP textual embeddings back into text, and we can learn how to do this by learning a decoder for the frozen CLIP text encoder using only text. We argue that this intuition is “almost correct” because of a gap between the embedding spaces, and propose to rectify this via noise injection during training. We demonstrate the effectiveness of our approach by showing SOTA zero-shot image captioning across four benchmarks, including style transfer. Code, data, and models are available at

pdf bib
Learning to Retrieve Passages without Supervision
Ori Ram | Gal Shachaf | Omer Levy | Jonathan Berant | Amir Globerson
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Dense retrievers for open-domain question answering (ODQA) have been shown to achieve impressive performance by training on large datasets of question-passage pairs. In this work we ask whether this dependence on labeled data can be reduced via unsupervised pretraining that is geared towards ODQA. We show this is in fact possible, via a novel pretraining scheme designed for retrieval. Our “recurring span retrieval” approach uses recurring spans across passages in a document to create pseudo examples for contrastive learning. Our pretraining scheme directly controls for term overlap across pseudo queries and relevant passages, thus allowing to model both lexical and semantic relations between them. The resulting model, named Spider, performs surprisingly well without any labeled training examples on a wide range of ODQA datasets. Specifically, it significantly outperforms all other pretrained baselines in a zero-shot setting, and is competitive with BM25, a strong sparse baseline. Moreover, a hybrid retriever over Spider and BM25 improves over both, and is often competitive with DPR models, which are trained on tens of thousands of examples. Last, notable gains are observed when using Spider as an initialization for supervised training.


pdf bib
BERTese: Learning to Speak to BERT
Adi Haviv | Jonathan Berant | Amir Globerson
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume

Large pre-trained language models have been shown to encode large amounts of world and commonsense knowledge in their parameters, leading to substantial interest in methods for extracting that knowledge. In past work, knowledge was extracted by taking manually-authored queries and gathering paraphrases for them using a separate pipeline. In this work, we propose a method for automatically rewriting queries into “BERTese”, a paraphrase query that is directly optimized towards better knowledge extraction. To encourage meaningful rewrites, we add auxiliary loss functions that encourage the query to correspond to actual language tokens. We empirically show our approach outperforms competing baselines, obviating the need for complex pipelines. Moreover, BERTese provides some insight into the type of language that helps language models perform knowledge extraction.

pdf bib
Few-Shot Question Answering by Pretraining Span Selection
Ori Ram | Yuval Kirstain | Jonathan Berant | Amir Globerson | Omer Levy
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

In several question answering benchmarks, pretrained models have reached human parity through fine-tuning on an order of 100,000 annotated questions and answers. We explore the more realistic few-shot setting, where only a few hundred training examples are available, and observe that standard models perform poorly, highlighting the discrepancy between current pretraining objectives and question answering. We propose a new pretraining scheme tailored for question answering: recurring span selection. Given a passage with multiple sets of recurring spans, we mask in each set all recurring spans but one, and ask the model to select the correct span in the passage for each masked span. Masked spans are replaced with a special token, viewed as a question representation, that is later used during fine-tuning to select the answer span. The resulting model obtains surprisingly good results on multiple benchmarks (e.g., 72.7 F1 on SQuAD with only 128 training examples), while maintaining competitive performance in the high-resource setting.


pdf bib
A Simple and Effective Model for Answering Multi-span Questions
Elad Segal | Avia Efrat | Mor Shoham | Amir Globerson | Jonathan Berant
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Models for reading comprehension (RC) commonly restrict their output space to the set of all single contiguous spans from the input, in order to alleviate the learning problem and avoid the need for a model that generates text explicitly. However, forcing an answer to be a single span can be restrictive, and some recent datasets also include multi-span questions, i.e., questions whose answer is a set of non-contiguous spans in the text. Naturally, models that return single spans cannot answer these questions. In this work, we propose a simple architecture for answering multi-span questions by casting the task as a sequence tagging problem, namely, predicting for each input token whether it should be part of the output or not. Our model substantially improves performance on span extraction questions from DROP and Quoref by 9.9 and 5.5 EM points respectively.

pdf bib
Pre-training Mention Representations in Coreference Models
Yuval Varkel | Amir Globerson
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Collecting labeled data for coreference resolution is a challenging task, requiring skilled annotators. It is thus desirable to develop coreference resolution models that can make use of unlabeled data. Here we provide such an approach for the powerful class of neural coreference models. These models rely on representations of mentions, and we show these representations can be learned in a self-supervised manner towards improving resolution accuracy. We propose two self-supervised tasks that are closely related to coreference resolution and thus improve mention representation. Applying this approach to the GAP dataset results in new state of the arts results.


pdf bib
Cross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-shot Dependency Parsing
Tal Schuster | Ori Ram | Regina Barzilay | Amir Globerson
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

We introduce a novel method for multilingual transfer that utilizes deep contextual embeddings, pretrained in an unsupervised fashion. While contextual embeddings have been shown to yield richer representations of meaning compared to their static counterparts, aligning them poses a challenge due to their dynamic nature. To this end, we construct context-independent variants of the original monolingual spaces and utilize their mapping to derive an alignment for the context-dependent spaces. This mapping readily supports processing of a target language, improving transfer by context-aware embeddings. Our experimental results demonstrate the effectiveness of this approach for zero-shot and few-shot learning of dependency parsing. Specifically, our method consistently outperforms the previous state-of-the-art on 6 tested languages, yielding an improvement of 6.8 LAS points on average.

pdf bib
Coreference Resolution with Entity Equalization
Ben Kantor | Amir Globerson
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

A key challenge in coreference resolution is to capture properties of entity clusters, and use those in the resolution process. Here we provide a simple and effective approach for achieving this, via an “Entity Equalization” mechanism. The Equalization approach represents each mention in a cluster via an approximation of the sum of all mentions in the cluster. We show how this can be done in a fully differentiable end-to-end manner, thus enabling high-order inferences in the resolution process. Our approach, which also employs BERT embeddings, results in new state-of-the-art results on the CoNLL-2012 coreference resolution task, improving average F1 by 3.6%.


pdf bib
Weakly Supervised Semantic Parsing with Abstract Examples
Omer Goldman | Veronica Latcinnik | Ehud Nave | Amir Globerson | Jonathan Berant
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Training semantic parsers from weak supervision (denotations) rather than strong supervision (programs) complicates training in two ways. First, a large search space of potential programs needs to be explored at training time to find a correct program. Second, spurious programs that accidentally lead to a correct denotation add noise to training. In this work we propose that in closed worlds with clear semantic types, one can substantially alleviate these problems by utilizing an abstract representation, where tokens in both the language utterance and program are lifted to an abstract form. We show that these abstractions can be defined with a handful of lexical rules and that they result in sharing between different examples that alleviates the difficulties in training. To test our approach, we develop the first semantic parser for CNLVR, a challenging visual reasoning dataset, where the search space is large and overcoming spuriousness is critical, because denotations are either TRUE or FALSE, and thus random programs are likely to lead to a correct denotation. Our method substantially improves performance, and reaches 82.5% accuracy, a 14.7% absolute accuracy improvement compared to the best reported accuracy so far.


pdf bib
Collective Entity Resolution with Multi-Focal Attention
Amir Globerson | Nevena Lazic | Soumen Chakrabarti | Amarnag Subramanya | Michael Ringgaard | Fernando Pereira
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)


pdf bib
Template Kernels for Dependency Parsing
Hillel Taub-Tabib | Yoav Goldberg | Amir Globerson
Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies


pdf bib
Exploring Compositional Architectures and Word Vector Representations for Prepositional Phrase Attachment
Yonatan Belinkov | Tao Lei | Regina Barzilay | Amir Globerson
Transactions of the Association for Computational Linguistics, Volume 2

Prepositional phrase (PP) attachment disambiguation is a known challenge in syntactic parsing. The lexical sparsity associated with PP attachments motivates research in word representations that can capture pertinent syntactic and semantic features of the word. One promising solution is to use word vectors induced from large amounts of raw text. However, state-of-the-art systems that employ such representations yield modest gains in PP attachment accuracy. In this paper, we show that word vector representations can yield significant PP attachment performance gains. This is achieved via a non-linear architecture that is discriminatively trained to maximize PP attachment accuracy. The architecture is initialized with word vectors trained from unlabeled data, and relearns those to maximize attachment accuracy. We obtain additional performance gains with alternative representations such as dependency-based word vectors. When tested on both English and Arabic datasets, our method outperforms both a strong SVM classifier and state-of-the-art parsers. For instance, we achieve 82.6% PP attachment accuracy on Arabic, while the Turbo and Charniak self-trained parsers obtain 76.7% and 80.8% respectively.

pdf bib
Steps to Excellence: Simple Inference with Refined Scoring of Dependency Trees
Yuan Zhang | Tao Lei | Regina Barzilay | Tommi Jaakkola | Amir Globerson
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)


pdf bib
Transfer Learning for Constituency-Based Grammars
Yuan Zhang | Regina Barzilay | Amir Globerson
Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)


pdf bib
Selective Sharing for Multilingual Dependency Parsing
Tahira Naseem | Regina Barzilay | Amir Globerson
Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf bib
Learning to Map into a Universal POS Tagset
Yuan Zhang | Roi Reichart | Regina Barzilay | Amir Globerson
Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning

pdf bib
Improved Parsing and POS Tagging Using Inter-Sentence Consistency Constraints
Alexander Rush | Roi Reichart | Michael Collins | Amir Globerson
Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning


pdf bib
Structured Prediction Models via the Matrix-Tree Theorem
Terry Koo | Amir Globerson | Xavier Carreras | Michael Collins
Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL)