--- title: "Eric Nichols — author profile and papers" description: "Eric Nichols, Honda (Japan): 2 papers on Elamur Research (2015–2017), h-index 14 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/eric-nichols/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/eric-nichols/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Eric Nichols # Eric Nichols Eric Nichols works on [named entity recognition](https://md.research.elamur.ai/free/en/topics/named-entity-recognition/), the task of finding names of people, places, organisations and similar items in English text and assigning each a type. Nichols's papers here follow two connected lines: designing neural taggers that depend less on hand-engineered resources, and testing how well such systems handle unfamiliar names in informal online writing. The more widely cited of the two, [Named Entity Recognition with Bidirectional LSTM-CNNs](https://md.research.elamur.ai/free/en/papers/chiu-2015-named-entity-recognition-bidirectional-lstm/) from 2015, proposes a tagger that learns much of what earlier systems obtained from manual features and large name lists. Each word is encoded by joining a pretrained embedding with a character-based vector built by a convolutional layer and max pooling. A stacked bidirectional LSTM then reads these vectors, and the scores from both reading directions are added to choose tags, with dropout used to limit overfitting. The later paper, [Results of the WNUT2017 Shared Task on Novel and Emerging Entity Recognition](https://md.research.elamur.ai/free/en/papers/derczynski-2017-results-wnut2017-shared-task-novel/) from 2017, turns from building models to measuring them. It argues that standard benchmarks reward systems for recognising common, repeated names, while performance drops on rare or newly coined ones in noisy social-media posts. The task design removes any evaluation text that contains an entity string seen in training. It scores each distinct pairing of name and type only once, and it draws development and test data from different online sources to build in a shift between them. This work was written with [Leon Derczynski](https://md.research.elamur.ai/free/en/authors/leon-derczynski/). Nichols is currently affiliated with Honda Research Institute Japan in Wako and with Honda in Tokyo. Earlier bylines list Tohoku University in Sendai (2011–2012) and the Nara Institute of Science and Technology in Ikoma (2004–2010). 2 papers on this site · 2015–2017 current affiliation [Honda (Japan)](https://md.research.elamur.ai/free/en/companies/honda/), Tokyo, Japan; [Honda Research Institute Japan Co., Ltd. (Japan)](https://md.research.elamur.ai/free/en/companies/honda-research-institute-japan-co-ltd/), Wako, Japan Eric Nichols has 2 papers on this site, in 2015–2017, most of them on [Named entity recognition](https://md.research.elamur.ai/free/en/topics/named-entity-recognition/); often with [Leon Derczynski](https://md.research.elamur.ai/free/en/authors/leon-derczynski/). [OpenAlex](https://openalex.org/A5056903330) · [ORCID](https://orcid.org/0000-0003-0734-6621) · [**h-index 14**](https://openalex.org/authors/A5056903330) · [69 works](https://openalex.org/works?filter=author.id:A5056903330) · [2 801 citations](https://openalex.org/works?filter=author.id:A5056903330&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [2 works on this site](https://md.research.elamur.ai/free/en/authors/eric-nichols/#papers) · [555 citations in our library](https://md.research.elamur.ai/free/en/authors/eric-nichols/cited-by/) · 1 more work in our library The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Eric+Nichols) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Eric+Nichols) · [dblp](https://dblp.org/search?q=Eric+Nichols) · [ACL Anthology](https://aclanthology.org/search/?q=Eric+Nichols) ## Affiliations - [Honda Research Institute Japan Co., Ltd. (Japan)](https://md.research.elamur.ai/free/en/companies/honda-research-institute-japan-co-ltd/) · Wako, Japan —current · 2015–2026 on 41 papers - [Honda (Japan)](https://md.research.elamur.ai/free/en/companies/honda/) · Tokyo, Japan —current · 2016–2026 on 24 papers - [Tohoku University](https://md.research.elamur.ai/free/en/universities/tohoku-university/) · Sendai, Japan —2011–2012 on 3 papers - [Nara Institute of Science and Technology](https://md.research.elamur.ai/free/en/universities/nara-institute-of-science-and-technology/) · Ikoma, Japan —2004–2010 on 8 papers From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 5 more institutions on single bylines are not listed. ## Topics [Named entity recognition 2](https://md.research.elamur.ai/free/en/topics/named-entity-recognition/) ## Works by year ### 2010s [**2017** 1 paper](https://md.research.elamur.ai/free/en/papers/derczynski-2017-results-wnut2017-shared-task-novel/) · [**2015** 1 paper](https://md.research.elamur.ai/free/en/papers/chiu-2015-named-entity-recognition-bidirectional-lstm/) ## Papers The most cited first (OpenAlex and our library). 1. **[Named Entity Recognition with Bidirectional LSTM-CNNs](https://md.research.elamur.ai/free/en/papers/chiu-2015-named-entity-recognition-bidirectional-lstm/)** *(2015 · 2 276 citations)* The paper addresses named entity recognition (NER) for English. Strong NER systems have usually relied on hand-built features and large gazetteers. The authors propose a neural tagger that learns most of these signals on its own. Each token is represented by a pretrained word embedding plus a character-level vector… 2. **[Results of the WNUT2017 Shared Task on Novel and Emerging Entity Recognition](https://md.research.elamur.ai/free/en/papers/derczynski-2017-results-wnut2017-shared-task-novel/)** *(2017 · 534 citations)* The paper examines a known weakness of named entity recognition: systems score well on standard benchmarks mainly because those benchmarks repeat frequent, familiar names, and they break down on rare or newly appearing entities in noisy social-media text. ## Also in our library 1 more work of theirs is in our library without a page here yet; it will appear as we publish them. ## Co-authors here 1 co-author with a page, the most papers together first. - [Leon Derczynski](https://md.research.elamur.ai/free/en/authors/leon-derczynski/) ## Cited by Papers of our library cite their works 555 times (of the 140 884 papers whose bibliographies we read); [36 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/eric-nichols/cited-by/).