Papers by Naoki Otani
Variance Matters: Detecting Semantic Differences without Corpus/Word Alignment (2023.emnlp-main)
Copied to clipboard
| Challenge: | a new method for finding semantic differences in words appears in two corpora, but it requires a variance of word vectors . a word covers more meanings in a corpus, and its mean word vector becomes shorter . |
| Approach: | They propose a method to measure the coverage of meanings of a word in a corpus through the norm of its mean word vector. |
| Outcome: | The proposed methods rival the best-performing system in the SemEval-2020 Task 1 . they are robust for the skew in corpus sizes and capable of detecting infrequent words . |
What A Sunny Day ☔: Toward Emoji-Sensitive Irony Detection (D19-55)
Copied to clipboard
| Challenge: | Existing datasets for irony detection only contain 10% of ironic tweets with emojis . 45% of internet users in the united states use an e-moji in social media . |
| Approach: | They propose to use emojis to analyze irony detection datasets to train classifiers. |
| Outcome: | The proposed pipeline can be used to analyze irony detection datasets using emojis. |
Pre-tokenization of Multi-word Expressions in Cross-lingual Word Embeddings (2020.emnlp-main)
Copied to clipboard
| Challenge: | Multi-Word Expressions (MWEs) are common in every language, but they are not translated by cross-lingual word embeddings. |
| Approach: | They propose a method for word translation of Multi-Word Expressions (MWEs) they compile lists of MWEs in each language and tokenize them as single tokens before training word embeddings. |
| Outcome: | The proposed method can translate multi-word expressions to and from English in 10 languages. |
Low-resource Cross-lingual Event Type Detection via Distant Supervision with Minimal Effort (C18-1)
Copied to clipboard
| Challenge: | Currently, few or no language processing tools or resources exist for most languages . a problem is that there is not enough available training data even in resource-rich languages if the task is complex. |
| Approach: | They propose to use a bilingual dictionary to train machine learning in a resource-poor language . they also explore adversarial training of bilingual word representations . |
| Outcome: | The proposed approach gives similar performance in event-type detection tasks. |
Cross-lingual Knowledge Projection Using Machine Translation and Target-side Knowledge Base Completion (C18-1)
Copied to clipboard
| Challenge: | Existing efforts to build commonsense knowledge bases are expensive and lack quantity and quality between languages. |
| Approach: | They propose to project English commonsense knowledge into Japanese and Chinese with high precision. |
| Outcome: | The proposed method achieves top-10 accuracy on the crowdsourced English–Japanese benchmark and 18,747 facts of accurate Japanese commonsense within a very short period. |
Toward Comprehensive Understanding of a Sentiment Based on Human Motives (P19-1)
Copied to clipboard
| Challenge: | a new study examines the motivations of sentiment holder and their relationship to food . aspects of a sentiment are limited to properties of entities such as the price of food and design of . |
| Approach: | They define six basic motives that cover a wide range of topics appearing in review texts . they annotate 1,600 texts in restaurant and laptop domains with the motives . |
| Outcome: | The proposed method improves on annotating 1,600 text with the motives and comparing them to other methods. |
LITE: Intent-based Task Representation Learning Using Weak Supervision (2022.naacl-main)
Copied to clipboard
| Challenge: | To-do texts are often short and under-specified, which poses a challenge for current text representation models. |
| Approach: | They propose a neural multi-task learning framework that extracts representations of English to-do tasks with a multi-head attention mechanism on top of a pre-trained text encoder. |
| Outcome: | The proposed model outperforms baseline models on four downstream tasks and achieves error reduction of 38.7%. |
Cross-lingual and Word-Independent Methods for Quantifying Degree of Grammaticalization (2026.eacl-long)
Copied to clipboard
Ryo Nagata, Daichi Mochihashi, Misato Ido, Yusuke Kubota, Naoki Otani, Yoshifumi Kawasaki, Hiroya Takamura
| Challenge: | Existing methods for quantifying the degree of grammaticalization are language- and word-dependent . existing methods are language dependent and lack training data . |
| Approach: | They propose to use Positive-Unlabeled learning or Cross-Validation-like learning to quantify degree of grammaticalization. |
| Outcome: | The proposed method achieves high correlations to human judgments in English deverbal prepositions and Japanese nouns being grammaticalized. |
Natural Language Processing for Human Resources: A Survey (2025.naacl-industry)
Copied to clipboard
| Challenge: | Recent advances in NLP have the potential to transform HR processes, from recruitment to employee management. |
| Approach: | They analyze key tasks such as information extraction and text classification and their roles in downstream applications like recommendation and language generation while discussing ethical concerns. |
| Outcome: | The proposed frameworks can be applied to HR tasks and to recommendation, language generation, and interaction. |
Unsupervised Cross-lingual Transfer of Word Embedding Spaces (D18-1)
Copied to clipboard
| Challenge: | Existing methods for cross-lingual word mapping require cross-linguistic supervision, but this is not available for many low resource languages. |
| Approach: | They propose an unsupervised method that learns transformation functions over corresponding word embedding spaces using a distributed distributional matching algorithm. |
| Outcome: | The proposed method performs better on bilingual lexicon induction and cross-lingual word similarity prediction datasets than other supervised and unsupervised methods. |
A Computational Approach to Quantifying Grammaticization of English Deverbal Prepositions (2024.lrec-main)
Copied to clipboard
| Challenge: | Linguistic studies have revealed important aspects of grammaticization of deverbal prepositions. |
| Approach: | They propose a computational approach to measure the degree of grammaticization of deverbal prepositions based on corpus data. |
| Outcome: | The proposed method correlates well with human judgements and supports previous findings in linguistics. |
A Textual Dataset for Situated Proactive Response Selection (2023.acl-long)
Copied to clipboard
| Challenge: | Recent data-driven conversational models can return fluent, consistent, and informative responses to many kinds of requests and utterances in task-oriented scenarios. |
| Approach: | They propose a task of proactive response selection based on situational information and a dataset of 1.7k English conversation examples that include situational background information and for each conversation a set of responses. |
| Outcome: | The proposed model can only provide fluent, consistent, and informative responses to a set of 1.7k English conversation examples and is not easy to perform for strong neural models. |