Minjoon Seo


2023

pdf
Towards standardizing Korean Grammatical Error Correction: Datasets and Annotation
Soyoung Yoon | Sungjoon Park | Gyuwan Kim | Junhee Cho | Kihyo Park | Gyu Tae Kim | Minjoon Seo | Alice Oh
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Research on Korean grammatical error correction (GEC) is limited, compared to other major languages such as English. We attribute this problematic circumstance to the lack of a carefully designed evaluation benchmark for Korean GEC. In this work, we collect three datasets from different sources (Kor-Lang8, Kor-Native, and Kor-Learner) that covers a wide range of Korean grammatical errors. Considering the nature of Korean grammar, We then define 14 error types for Korean and provide KAGAS (Korean Automatic Grammatical error Annotation System), which can automatically annotate error types from parallel corpora. We use KAGAS on our datasets to make an evaluation benchmark for Korean, and present baseline models trained from our datasets. We show that the model trained with our datasets significantly outperforms the currently used statistical Korean GEC system (Hanspell) on a wider range of error types, demonstrating the diversity and usefulness of the datasets. The implementations and datasets are open-sourced.

pdf
Knowledge Unlearning for Mitigating Privacy Risks in Language Models
Joel Jang | Dongkeun Yoon | Sohee Yang | Sungmin Cha | Moontae Lee | Lajanugen Logeswaran | Minjoon Seo
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Pretrained Language Models (LMs) memorize a vast amount of knowledge during initial pretraining, including information that may violate the privacy of personal lives and identities. Previous work addressing privacy issues for LMs has mostly focused on data preprocessing and differential privacy methods, both requiring re-training the underlying LM. We propose knowledge unlearning as an alternative method to reduce privacy risks for LMs post hoc. We show that simply performing gradient ascent on target token sequences is effective at forgetting them with little to no degradation of general language modeling performances for larger-sized LMs. We also find that sequential unlearning is better than trying to unlearn all the data at once and that unlearning is highly dependent on which kind of data (domain) is forgotten. By showing comparisons with previous methods known to mitigate privacy risks for LMs, we show that our approach can give a stronger empirical privacy guarantee in scenarios where the data vulnerable to extraction attacks are known a priori while being much more efficient and robust.

pdf
Gradient Ascent Post-training Enhances Language Model Generalization
Dongkeun Yoon | Joel Jang | Sungdong Kim | Minjoon Seo
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

In this work, we empirically show that updating pretrained LMs (350M, 1.3B, 2.7B) with just a few steps of Gradient Ascent Post-training (GAP) on random, unlabeled text corpora enhances its zero-shot generalization capabilities across diverse NLP tasks. Specifically, we show that GAP can allow LMs to become comparable to 2-3x times larger LMs across 12 different NLP tasks. We also show that applying GAP on out-of-distribution corpora leads to the most reliable performance improvements. Our findings indicate that GAP can be a promising method for improving the generalization capability of LMs without any task-specific fine-tuning.

pdf
Two Examples are Better than One: Context Regularization for Gradient-based Prompt Tuning
Hyeonmin Ha | Soyoung Jung | Jinsol Park | Minjoon Seo | Seung-won Hwang | Byung-Gon Chun
Findings of the Association for Computational Linguistics: ACL 2023

Prompting has gained tremendous attention as an efficient method for the adaptation of large-scale language models.However, prompts often act against human intuition and report unstable performances, which has motivated methods that automatically find effective prompts.One popular approach is gradient-based search, which iteratively updates a (randomly) initialized prompt towards the optimal one with the guide of gradients.We propose a novel regularization method, CoRe, for gradient-based prompt tuning techniques, which guides a prompt to produce a task context properly.CoRe realizes two regularization effects — context attuning and context filtering — that improve prediction performance in a zero-shot in-context learning setting where a model makes inferences only with the prompt tuned by CoRe, without any demonstration examples for in-context learning.Context attuning guides the context generated by the input and the tuned prompt toward embedding the appropriate context for the task.In our theoretical analysis, regularizing the context extends to improving zero-shot in-context learning performance.Context filtering steers the prompt to select only the task-related context so that context attuning solely focuses on creating and sending the right task context.We evaluate CoRe on natural language understanding datasets and two large language models, GPT2-XL and GPT-J.Our training scheme shows performance improvements up to 11.9% on GPT2-XL, and up to 6.3% on GPT-J in zero-shot settings.

pdf
ClaimDiff: Comparing and Contrasting Claims on Contentious Issues
Miyoung Ko | Ingyu Seong | Hwaran Lee | Joonsuk Park | Minsuk Chang | Minjoon Seo
Findings of the Association for Computational Linguistics: ACL 2023

With the growing importance of detecting misinformation, many studies have focused on verifying factual claims by retrieving evidence. However, canonical fact verification tasks do not apply to catching subtle differences in factually consistent claims, which might still bias the readers, especially on contentious political or economic issues. Our underlying assumption is that among the trusted sources, one’s argument is not necessarily more true than the other, requiring comparison rather than verification. In this study, we propose ClaimDIff, a novel dataset that primarily focuses on comparing the nuance between claim pairs. In ClaimDiff, we provide human-labeled 2,941 claim pairs from 268 news articles. We observe that while humans are capable of detecting the nuances between claims, strong baselines struggle to detect them, showing over a 19% absolute gap with the humans. We hope this initial study could help readers to gain an unbiased grasp of contentious issues through machine-aided comparison.

pdf
Fixed Input Parameterization for Efficient Prompting
Eunbi Choi | Yongrae Jo | Joel Jang | Joonwon Jang | Minjoon Seo
Findings of the Association for Computational Linguistics: ACL 2023

Recent works have shown that attaching prompts to the input is effective at conditioning Language Models (LM) to perform specific tasks. However, prompts are always included in the input text during inference, even when they are fixed, thus incurring substantial computational and memory overhead. Also, there is currently no straightforward method of utilizing prompts that are longer than the maximum input length of the LMs without incurring additional costs during inference. We formally define Fixed Input Parameterization (FIP) problem that focuses on injecting the fixed prompt into the parameters of an LM to be an efficient alternative to attaching fixed prompts to the input. We show that in scenarios with long fixed prompts, FIP can be up to 280 times more efficient in terms of total FLOPs than previous approaches. We further explore methodologies for FIP and show promising results in persona-dependent conversation, semantic parsing, and zero-shot learning with task instructions. Through these explorations, we show that FIP can be a promising direction for conditioning language models, in scenarios with long and fixed prompts.

pdf
Nonparametric Decoding for Generative Retrieval
Hyunji Lee | JaeYoung Kim | Hoyeon Chang | Hanseok Oh | Sohee Yang | Vladimir Karpukhin | Yi Lu | Minjoon Seo
Findings of the Association for Computational Linguistics: ACL 2023

The generative retrieval model depends solely on the information encoded in its model parameters without external memory, its information capacity is limited and fixed. To overcome the limitation, we propose Nonparametric Decoding (Np Decoding) which can be applied to existing generative retrieval models. Np Decoding uses nonparametric contextualized vocab embeddings (external memory) rather than vanilla vocab embeddings as decoder vocab embeddings. By leveraging the contextualized vocab embeddings, the generative retrieval model is able to utilize both the parametric and nonparametric space. Evaluation over 9 datasets (8 single-hop and 1 multi-hop) in the document retrieval task shows that applying Np Decoding to generative retrieval models significantly improves the performance. We also show that Np Decoding is data- and parameter-efficient, and shows high performance in the zero-shot setting.

2022

pdf
Data-efficient end-to-end Information Extraction for Statistical Legal Analysis
Wonseok Hwang | Saehee Eom | Hanuhl Lee | Hai Jin Park | Minjoon Seo
Proceedings of the Natural Legal Language Processing Workshop 2022

Legal practitioners often face a vast amount of documents. Lawyers, for instance, search for appropriate precedents favorable to their clients, while the number of legal precedents is ever-growing. Although legal search engines can assist finding individual target documents and narrowing down the number of candidates, retrieved information is often presented as unstructured text and users have to examine each document thoroughly which could lead to information overloading. This also makes their statistical analysis challenging. Here, we present an end-to-end information extraction (IE) system for legal documents. By formulating IE as a generation task, our system can be easily applied to various tasks without domain-specific engineering effort. The experimental results of four IE tasks on Korean precedents shows that our IE system can achieve competent scores (-2.3 on average) compared to the rule-based baseline with as few as 50 training examples per task and higher score (+5.4 on average) with 200 examples. Finally, our statistical analysis on two case categories — drunk driving and fraud — with 35k precedents reveals the resulting structured information from our IE system faithfully reflects the macroscopic features of Korean legal system.

pdf
Generative Multi-hop Retrieval
Hyunji Lee | Sohee Yang | Hanseok Oh | Minjoon Seo
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

A common practice for text retrieval is to use an encoder to map the documents and the query to a common vector space and perform a nearest neighbor search (NNS); multi-hop retrieval also often adopts the same paradigm, usually with a modification of iteratively reformulating the query vector so that it can retrieve different documents at each hop. However, such a bi-encoder approach has limitations in multi-hop settings; (1) the reformulated query gets longer as the number of hops increases, which further tightens the embedding bottleneck of the query vector, and (2) it is prone to error propagation. In this paper, we focus on alleviating these limitations in multi-hop settings by formulating the problem in a fully generative way. We propose an encoder-decoder model that performs multi-hop retrieval by simply generating the entire text sequences of the retrieval targets, which means the query and the documents interact in the language model’s parametric space rather than L2 or inner product space as in the bi-encoder approach. Our approach, Generative Multi-hop Retrieval (GMR), consistently achieves comparable or higher performance than bi-encoder models in five datasets while demonstrating superior GPU memory and storage footprint.

pdf
TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models
Joel Jang | Seonghyeon Ye | Changho Lee | Sohee Yang | Joongbo Shin | Janghoon Han | Gyeonghun Kim | Minjoon Seo
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Language Models (LMs) become outdated as the world changes; they often fail to perform tasks requiring recent factual information which was absent or different during training, a phenomenon called temporal misalignment. This is especially a challenging problem because the research community still lacks a coherent dataset for assessing the adaptability of LMs to frequently-updated knowledge corpus such as Wikipedia. To this end, we introduce TemporalWiki, a lifelong benchmark for ever-evolving LMs that utilizes the difference between consecutive snapshots of English Wikipedia and English Wikidata for training and evaluation, respectively. The benchmark hence allows researchers to periodically track an LM’s ability to retain previous knowledge and acquire updated/new knowledge at each point in time. We also find that training an LM on the diff data through continual learning methods achieves similar or better perplexity than on the entire snapshot in our benchmark with 12 times less computational cost, which verifies that factual knowledge in LMs can be safely updated with minimal training data via continual learning.

2021

pdf bib
Proceedings of the 3rd Workshop on Machine Reading for Question Answering
Adam Fisch | Alon Talmor | Danqi Chen | Eunsol Choi | Minjoon Seo | Patrick Lewis | Robin Jia | Sewon Min
Proceedings of the 3rd Workshop on Machine Reading for Question Answering

pdf
Spatial Dependency Parsing for Semi-Structured Document Information Extraction
Wonseok Hwang | Jinyeong Yim | Seunghyun Park | Sohee Yang | Minjoon Seo
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf
Cost-effective End-to-end Information Extraction for Semi-structured Document Images
Wonseok Hwang | Hyunji Lee | Jinyeong Yim | Geewook Kim | Minjoon Seo
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

A real-world information extraction (IE) system for semi-structured document images often involves a long pipeline of multiple modules, whose complexity dramatically increases its development and maintenance cost. One can instead consider an end-to-end model that directly maps the input to the target output and simplify the entire process. However, such generation approach is known to lead to unstable performance if not designed carefully. Here we present our recent effort on transitioning from our existing pipeline-based IE system to an end-to-end system focusing on practical challenges that are associated with replacing and deploying the system in real, large-scale production. By carefully formulating document IE as a sequence generation task, we show that a single end-to-end IE system can be built and still achieve competent performance.

pdf
Designing a Minimal Retrieve-and-Read System for Open-Domain Question Answering
Sohee Yang | Minjoon Seo
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

In open-domain question answering (QA), retrieve-and-read mechanism has the inherent benefit of interpretability and the easiness of adding, removing, or editing knowledge compared to the parametric approaches of closed-book QA models. However, it is also known to suffer from its large storage footprint due to its document corpus and index. Here, we discuss several orthogonal strategies to drastically reduce the footprint of a retrieve-and-read open-domain QA system by up to 160x. Our results indicate that retrieve-and-read can be a viable option even in a highly constrained serving environment such as edge devices, as we show that it can achieve better accuracy than a purely parametric model with comparable docker-level system size.

2020

pdf
Contextualized Sparse Representations for Real-Time Open-Domain Question Answering
Jinhyuk Lee | Minjoon Seo | Hannaneh Hajishirzi | Jaewoo Kang
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Open-domain question answering can be formulated as a phrase retrieval problem, in which we can expect huge scalability and speed benefit but often suffer from low accuracy due to the limitation of existing phrase representation models. In this paper, we aim to improve the quality of each phrase embedding by augmenting it with a contextualized sparse representation (Sparc). Unlike previous sparse vectors that are term-frequency-based (e.g., tf-idf) or directly learned (only few thousand dimensions), we leverage rectified self-attention to indirectly learn sparse vectors in n-gram vocabulary space. By augmenting the previous phrase retrieval model (Seo et al., 2019) with Sparc, we show 4%+ improvement in CuratedTREC and SQuAD-Open. Our CuratedTREC score is even better than the best known retrieve & read model with at least 45x faster inference speed.

pdf bib
Proceedings of the 5th Workshop on Representation Learning for NLP
Spandana Gella | Johannes Welbl | Marek Rei | Fabio Petroni | Patrick Lewis | Emma Strubell | Minjoon Seo | Hannaneh Hajishirzi
Proceedings of the 5th Workshop on Representation Learning for NLP

2019

pdf
Mixture Content Selection for Diverse Sequence Generation
Jaemin Cho | Minjoon Seo | Hannaneh Hajishirzi
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Generating diverse sequences is important in many NLP applications such as question generation or summarization that exhibit semantically one-to-many relationships between source and the target sequences. We present a method to explicitly separate diversification from generation using a general plug-and-play module (called SELECTOR) that wraps around and guides an existing encoder-decoder model. The diversification stage uses a mixture of experts to sample different binary masks on the source sequence for diverse content selection. The generation stage uses a standard encoder-decoder model given each selected content from the source sequence. Due to the non-differentiable nature of discrete sampling and the lack of ground truth labels for binary mask, we leverage a proxy for ground truth mask and adopt stochastic hard-EM for training. In question generation (SQuAD) and abstractive summarization (CNN-DM), our method demonstrates significant improvements in accuracy, diversity and training efficiency, including state-of-the-art top-1 accuracy in both datasets, 6% gain in top-5 accuracy, and 3.7 times faster training over a state-of-the-art model. Our code is publicly available at https://github.com/clovaai/FocusSeq2Seq.

pdf bib
Proceedings of the 2nd Workshop on Machine Reading for Question Answering
Adam Fisch | Alon Talmor | Robin Jia | Minjoon Seo | Eunsol Choi | Danqi Chen
Proceedings of the 2nd Workshop on Machine Reading for Question Answering

pdf bib
MRQA 2019 Shared Task: Evaluating Generalization in Reading Comprehension
Adam Fisch | Alon Talmor | Robin Jia | Minjoon Seo | Eunsol Choi | Danqi Chen
Proceedings of the 2nd Workshop on Machine Reading for Question Answering

We present the results of the Machine Reading for Question Answering (MRQA) 2019 shared task on evaluating the generalization capabilities of reading comprehension systems. In this task, we adapted and unified 18 distinct question answering datasets into the same format. Among them, six datasets were made available for training, six datasets were made available for development, and the rest were hidden for final evaluation. Ten teams submitted systems, which explored various ideas including data sampling, multi-task learning, adversarial training and ensembling. The best system achieved an average F1 score of 72.5 on the 12 held-out datasets, 10.7 absolute points higher than our initial baseline based on BERT.

pdf
Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index
Minjoon Seo | Jinhyuk Lee | Tom Kwiatkowski | Ankur Parikh | Ali Farhadi | Hannaneh Hajishirzi
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Existing open-domain question answering (QA) models are not suitable for real-time usage because they need to process several long documents on-demand for every input query, which is computationally prohibitive. In this paper, we introduce query-agnostic indexable representations of document phrases that can drastically speed up open-domain QA. In particular, our dense-sparse phrase encoding effectively captures syntactic, semantic, and lexical information of the phrases and eliminates the pipeline filtering of context documents. Leveraging strategies for optimizing training and inference time, our model can be trained and deployed even in a single 4-GPU server. Moreover, by representing phrases as pointers to their start and end tokens, our model indexes phrases in the entire English Wikipedia (up to 60 billion phrases) using under 2TB. Our experiments on SQuAD-Open show that our model is on par with or more accurate than previous models with 6000x reduced computational cost, which translates into at least 68x faster end-to-end inference benchmark on CPUs. Code and demo are available at nlp.cs.washington.edu/denspi

2018

pdf bib
Proceedings of the Workshop on Machine Reading for Question Answering
Eunsol Choi | Minjoon Seo | Danqi Chen | Robin Jia | Jonathan Berant
Proceedings of the Workshop on Machine Reading for Question Answering

pdf
Phrase-Indexed Question Answering: A New Challenge for Scalable Document Comprehension
Minjoon Seo | Tom Kwiatkowski | Ankur Parikh | Ali Farhadi | Hannaneh Hajishirzi
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

We formalize a new modular variant of current question answering tasks by enforcing complete independence of the document encoder from the question encoder. This formulation addresses a key challenge in machine comprehension by building a standalone representation of the document discourse. It additionally leads to a significant scalability advantage since the encoding of the answer candidate phrases in the document can be pre-computed and indexed offline for efficient retrieval. We experiment with baseline models for the new task, which achieve a reasonable accuracy but significantly underperform unconstrained QA models. We invite the QA research community to engage in Phrase-Indexed Question Answering (PIQA, pika) for closing the gap. The leaderboard is at: nlp.cs.washington.edu/piqa


Standardized Tests as benchmarks for Artificial Intelligence
Mrinmaya Sachan | Minjoon Seo | Hannaneh Hajishirzi | Eric Xing
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: Tutorial Abstracts

Standardized tests have recently been proposed as replacements to the Turing test as a driver for progress in AI (Clark, 2015). These include tests on understanding passages and stories and answering questions about them (Richardson et al., 2013; Rajpurkar et al., 2016a, inter alia), science question answering (Schoenick et al., 2016, inter alia), algebra word problems (Kushman et al., 2014, inter alia), geometry problems (Seo et al., 2015; Sachan et al., 2016), visual question answering (Antol et al., 2015), etc. Many of these tests require sophisticated understanding of the world, aiming to push the boundaries of AI. For this tutorial, we broadly categorize these tests into two categories: open domain tests such as reading comprehensions and elementary school tests where the goal is to find the support for an answer from the student curriculum, and closed domain tests such as intermediate level math and science tests (algebra, geometry, Newtonian physics problems, etc.). Unlike open domain tests, closed domain tests require the system to have significant domain knowledge and reasoning capabilities. For example, geometry questions typically involve a number of geometry primitives (lines, quadrilaterals, circles, etc) and require students to use axioms and theorems of geometry (Pythagoras theorem, alternating angles, etc) to solve them. These closed domains often have a formal logical basis and the question can be mapped to a formal language by semantic parsing. The formal question representation can then provided as an input to an expert system to solve the question.

2017

pdf
Question Answering through Transfer Learning from Large Fine-grained Supervision Data
Sewon Min | Minjoon Seo | Hannaneh Hajishirzi
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

We show that the task of question answering (QA) can significantly benefit from the transfer learning of models trained on a different large, fine-grained QA dataset. We achieve the state of the art in two well-studied QA datasets, WikiQA and SemEval-2016 (Task 3A), through a basic transfer learning technique from SQuAD. For WikiQA, our model outperforms the previous best model by more than 8%. We demonstrate that finer supervision provides better guidance for learning lexical and syntactic information than coarser supervision, through quantitative results and visual analysis. We also show that a similar transfer learning procedure achieves the state of the art on an entailment task.

pdf
Zero-Shot Relation Extraction via Reading Comprehension
Omer Levy | Minjoon Seo | Eunsol Choi | Luke Zettlemoyer
Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)

We show that relation extraction can be reduced to answering simple reading comprehension questions, by associating one or more natural-language questions with each relation slot. This reduction has several advantages: we can (1) learn relation-extraction models by extending recent neural reading-comprehension techniques, (2) build very large training sets for those models by combining relation-specific crowd-sourced questions with distant supervision, and even (3) do zero-shot learning by extracting new relation types that are only specified at test-time, for which we have no labeled training examples. Experiments on a Wikipedia slot-filling task demonstrate that the approach can generalize to new questions for known relation types with high accuracy, and that zero-shot generalization to unseen relation types is possible, at lower accuracy levels, setting the bar for future work on this task.

2015

pdf
Solving Geometry Problems: Combining Text and Diagram Interpretation
Minjoon Seo | Hannaneh Hajishirzi | Ali Farhadi | Oren Etzioni | Clint Malcolm
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing