What is she best known for?
The fields of study she is best known for:
- Artificial intelligence
- Linguistics
- Natural language processing
Teruko Mitamura mainly focuses on Artificial intelligence, Natural language processing, Information retrieval, Task and Event.
Her Artificial intelligence research includes elements of Machine learning and Linguistics, Vocabulary.
Her work on Machine translation, Example-based machine translation and Transfer-based machine translation as part of general Natural language processing research is frequently linked to Binary classification, bridging the gap between disciplines.
Her studies deal with areas such as Planner and TRECVID as well as Information retrieval.
Her Task research includes themes of Paraphrase, Logical consequence, Inference and Contradiction.
Her studies deal with areas such as Multimedia search, Image and Index as well as Event.
Her most cited work include:
- What is the Jeopardy Model? A Quasi-Synchronous Grammar for QA (353 citations)
- Integrated authoring and translation system (352 citations)
- Easy Samples First: Self-paced Reranking for Zero-Example Multimedia Search (175 citations)
What are the main themes of her work throughout her whole career to date?
Teruko Mitamura mostly deals with Artificial intelligence, Natural language processing, Information retrieval, Task and Question answering.
As part of the same scientific family, she usually focuses on Artificial intelligence, concentrating on Domain and intersecting with Domain knowledge.
Her Natural language processing study combines topics in areas such as Annotation and Coreference.
Her Information retrieval research integrates issues from Information access, Event and TRECVID.
Her work on Factoid as part of general Question answering study is frequently linked to Javelin, therefore connecting diverse disciplines of science.
Her Machine translation study incorporates themes from Syntax, Universal Networking Language, Multilingualism and Lexicon.
She most often published in these fields:
- Artificial intelligence (60.95%)
- Natural language processing (55.62%)
- Information retrieval (24.26%)
What were the highlights of her more recent work (between 2017-2021)?
- Artificial intelligence (60.95%)
- Natural language processing (55.62%)
- Task (20.71%)
In recent papers she was focusing on the following fields of study:
Teruko Mitamura focuses on Artificial intelligence, Natural language processing, Task, Question answering and Inference.
Her work deals with themes such as Argument, Machine learning and Interoperability, which intersect with Artificial intelligence.
Her study focuses on the intersection of Natural language processing and fields such as Textual entailment with connections in the field of Domain knowledge and Question generation.
Her Task study combines topics from a wide range of disciplines, such as Segmentation, Word and Set.
Her Question answering study deals with the bigger picture of Information retrieval.
Her Inference research is multidisciplinary, incorporating elements of Domain, Logical consequence and Feature.
Between 2017 and 2021, her most popular works were:
- Open-Domain Event Detection using Distant Supervision (18 citations)
- BioAMA: Towards an End to End BioMedical Question Answering System (9 citations)
- Low-resource Cross-lingual Event Type Detection via Distant Supervision with Minimal Effort (9 citations)
In her most recent research, the most cited papers focused on:
- Artificial intelligence
- Linguistics
- Programming language
Teruko Mitamura mostly deals with Artificial intelligence, Natural language processing, Task, Question answering and Inference.
Her research integrates issues of Speech recognition and Graph in her study of Artificial intelligence.
Teruko Mitamura combines subjects such as Event and Graph based with her study of Natural language processing.
Her Task research is multidisciplinary, incorporating perspectives in Word and Set.
Her work in Question answering tackles topics such as Ranking which are related to areas like Factoid and Mean reciprocal rank.
Teruko Mitamura has included themes like Domain, Logical consequence, Margin and Multi-task learning in her Inference study.
This overview was generated by a machine learning system which analysed the scientist’s
body of work. If you have any feedback, you can
contact us
here.
