BIOSMILE: A semantic role labeling system for biomedical verbs using a maximum-entropy model with automatically generated template features

Semantic role labeling (SRL) is a task in natural-language processing with the aim of detecting predicates in the text, choosing their correct senses, identifying their associated arguments, and predicting the semantic roles of the arguments. Developing a high-performance SRL system for a domain requires manually annotated training data of large size in the same domain. However, such SRL training data of sufficient size is available only for a few domains. Constructing SRL training data for a new domain is very expensive. Therefore, domain adaptation in SRL can be regarded as an important problem. In this paper, we show that domain adaptation for SRL systems can achieve state-of-the-art performance when based on structural learning and exploiting a prior model approach. We provide experimental results with three different target domains showing that our method is effective even if training data of small size is available for the target domains. According to experimentations, our proposed method outperforms those of other research works by about 2% to 5% in F-score.Keywords: Domain adaptation, semantic role labeling, natural language, semantic analysis, structured learning, prior model. I. IntroductionBig data explosion has led to an exponential growth in the amount of valuable textual data in many fields. Thus, automatic information retrieval (IR) and information extraction (IE) methods have become more important in helping researchers and analysts to keep track of the latest developments in their fields. Current IR is still mostly limited to keyword search and unable to infer relationships between entities in a text. A system that is able to understand how words in a sentence are related semantically can greatly improve the quality of IE and would allow IR to handle more complex user queries.Semantic role labeling (SRL) is a task for semantic processing of natural-language text, wherein the semantic role labels of the arguments associated with the predicates in a sentence are predicted. Recently, SRL has become increasingly popular as natural-language processing technology advances. The purpose of SRL is to find "who does what to whom, when, and where" in natural-language text by recognizing the semantic roles of the arguments of the predicates.As a result of performing SRL on a given sentence and its predicate, each word in the sentence is assigned a semantic role label. By combining the labels for the words, the output of SRL can be viewed as a sequence of semantic role labels. The sequence is generated for each predicate. For example, as in Fig. 1, the semantic role A0 represents the "agent" of "wants" and the semantic role A1 denotes the thing "being wanted." The information produced as a result of an SRL task is valuable for IE and other natural-language understanding tasks such as question answering [1] and online advertising services [2].In previous research, most works on SRL focused on

show abstract

“…To have this categorization of predicates, we refer to the data provided in [22]; the result of which is given in Table 4.…”

Section: Resultsmentioning

confidence: 99%

Domain-Adaptation Technique for Semantic Role Labeling with Structural Learning

Lim

Lee

Ryu

et al. 2014

ETRI J

View full text Add to dashboard Cite

show abstract

“…Furthermore, it can verify whether answer candidates extracted by NER are of the expected type. The F-score of our SRL system [16], which operates fully automatically, is 69.7% on the GENIA corpus. By comparing a candidate's semantic argument type with the expected type, we can eliminate many incorrect candidates and improve the overall accuracy.…”

Section: Candidate Extraction and Feature Generationmentioning

confidence: 99%

BESearch: A Supervised Learning Approach to Search for Molecular Event Participants

Tsai¹,

Dai²,

Hung³

et al. 2007

2007 IEEE International Conference on Information Reuse and Integration

Self Cite

View full text Add to dashboard Cite

Biomedical researchers rely on keyword-based search engines to retrieve superficially relevant documents, from which they must filter out irrelevant information manually. Hence, there is an urgent need for a more efficient system to help them rapidly locate specific molecular events and the participants involved in these events. In this paper, we propose a novel search system with a new search interface and answer ranking scheme. Due to the limited number of query types in the Biomedical-specific searches, we employ a form-based interface with various query templates for specifying required information. This can ascertain a user's intentions more accurately than a conventional keyword-based interface. Ranking is another key issue in this type of search. We propose a linear ranking model, trained by a supervised learning algorithm, which combines different features. Two semantic features, named entity types and semantic roles, are incorporated into the model to help match a query with entities in relevant documents. After employing all effective semantic features, our system achieves a Top-1 accuracy of 43.1% and Top-5 MRR of 47.1%. In comparison with the baseline system, Top-1 accuracy and Top-5 MRR increase by 9.5% and 7.1%.

show abstract

“…The answer types of 400 biomolecular event questions cover four NE classes, namely protein, DNA, RNA, and cell (including cell line and cell type). Furthermore, each question is based on one of 30 common biomolecular verbs described in [11].…”

Section: Datasetmentioning

confidence: 99%

“…In our system, each candidate is output with the sentence containing it, and the sentence is treated as its supporting evidence. We developed an SRL component [11] (F-score: 84.76%) to generate semantic features for answer ranking. SRL can recognize the predicate of a sentence and its corresponding argument phrases, such as the agent, recipient, and location.…”

Section: Candidate Extraction and Feature Generationmentioning

confidence: 99%