Skill mapping is a key task in the Human Resources domain. It consists in identifying ontology-defined skills in job texts. Among the most successful approaches applied to skill mapping, bi-encoders offer efficient inference but struggle with fine-grained skill distinctions, particularly under limited supervision. While accurate, cross-encoder and LLM-based reranking approaches are computationally expensive and usually not feasible to be adopted in real case scenarios. We propose kNNBE, a hybrid inference method that augments bi-encoder similarity scores with k-nearest labeled sentences drawn from a synthetic memory bank. kNNBE improves both prediction accuracy and generalization to unseen skills while retaining high throughput. Extensive experiments on three benchmark datasets show that kNNBE rivals state-of-the-art rerankers in accuracy while being orders of magnitude faster.

Chunpeng Ma, Takuya Makino. Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

We propose a global optimization method under length constraint (GOLC) for neural text summarization models. GOLC increases the probabilities of generating summaries that have high evaluation scores, ROUGE in this paper, within a desired length. We compared GOLC with two optimization methods, a maximum log-likelihood and a minimum risk training, on CNN/Daily Mail and a Japanese single document summarization data set of The Mainichi Shimbun Newspapers. The experimental results show that a state-of-the-art neural summarization model optimized with GOLC generates fewer overlength summaries while maintaining the fastest processing speed; only 6.70% overlength summaries on CNN/Daily and 7.8% on long summary of Mainichi, compared to the approximately 20% to 50% on CNN/Daily Mail and 10% to 30% on Mainichi with the other optimization methods. We also demonstrate the importance of the generation of in-length summaries for post-editing with the dataset Mainich that is created with strict length constraints. The ex- perimental results show approximately 30% to 40% improved post-editing time by use of in-length summaries.

Taiki Watanabe, Akihiro Tamura, Takashi Ninomiya, Takuya Makino, Tomoya Iwakura. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

In Targeted Entity Disambiguation setting, we take (i) a set of entity names which belong to the same domain (target entities), (ii) candidate mentions of the given entities which are texts that contain the target entities as input, and then determine which ones are true mentions of "target entity".For example, given the names of IT companies, including Apple, we determine Apple in a mention denotes an IT company or not.Prior work proposed a graph based model.This model ranks all candidate mentions based on scores which denote the degree of relevancy to target entities.Furthermore, this graph based model could utilize reference pages of target entities.However, human annotators must select reference pages in advance.We propose an automatic method that can select reference pages.We formalize the selection problem of reference pages as an Integer Linear Programming problem.We show that our model works as well as the prior work that manually selected reference pages.

We propose a new model for the guided text summarization task. In this task, it is required that a generated summary covers all the aspects, which are predefined for the topic of the given document cluster; for example, aspects for the topic "Accidents and Natural Disasters" include WHAT, WHEN, WHERE, WHY, WHO AFFECTED, DAMAGES and COUNTERMEASURES. We use as a scorer for an aspect, the maximum entropy classifier that predicts whether each sentence reflects the aspect or not. We formalize the coverage of the aspects as a max-min problem, which enables a summary to cover aspects in a well-balanced manner. In the max-min problem, the minimum of the aspect scores is going to be maximized so that the summary contains all the aspects as much as possible. Furthermore, we integrate the model based on the max-min problem with the maximum coverage summarization model, which generates a summary containing as many conceptual units as possible. Through the experiments on benchmark datasets for the guided summarization, we show that our model outperforms other approaches in terms of ROUGE-2.