Papers by Naoki Otani

12 papers
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

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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations