Opinion Summarization Using Entity Features and Probabilistic Sentence Coherence Optimization: UIUC at TAC 2008 Opinion Summarization Pilot
نویسندگان
چکیده
This paper talks about participation of the University of Illinois at Urbana-Champaign (UIUC) in TAC 2008 Opinion Summarization pilot. We mainly explored two ideas: (1) use of entity recognition and parsing to enhance a standard retrieval method for opinion retrieval, and (2) use of a coherence language model to optimize the ordering of sentences in a summary. Our result showed that use of entity recognition during retrieval led to mixed results and re-ordering with coherence language model was not as good as heuristic polarity-based ordering using guiding phrases. Our additional experiments showed that the performance of coherence language model can be different depending on probability function and word selection.
منابع مشابه
Summarization Focusing on Polarity or Opinion Fragments in Blogs
We present the TUT opinion summarization system which participated in the TAC 2008. The system consists of two modules: opinion/polarity automatic annotation module and fragment extraction module for summarization. Our research objective is to estimate the effectiveness of opinion/polarity annotation per sentence units for opinion summarization. The evaluation results showed that the polarity a...
متن کاملUsing Coreference Links and Sentence Compression in Graph-based Summarization
Recent years have shown that graphs are an adequate text representation model for summarization. For this years’ TAC update summarization challenge, we extended our graph-based summarization system with coreference relations and sentence compression. Our results show that using coreference relations did not result in a significant performance gain; sentence compression had a negative effect on ...
متن کاملIIIT Hyderabad at TAC 2008
This paper describes our participation at TAC 2008 in all the three tracks. For the Summarization Track we introduced two major features. First, a feature based on Information Loss if we don’t pick a particular sentence. Second, a language modeling extension that boosts novel terms and penalizes stale terms. During our post-TAC analysis we observed that a simple sentence position based summariz...
متن کاملThomson Reuters at TAC 2008: Aggressive Filtering with FastSum for Update and Opinion Summarization
In TAC 2008 we participated in the main task (Update Summarization) as well as the Sentiment Summarization pilot task. We modified the FastSum system (Schilder and Kondadadi, 2008) and added more aggressive filtering in order to adapt the system to update summarization and sentiment summarization. For the Update Summarization task, we show that a classifier that identifies sentences that are si...
متن کاملNUS at TAC 2008: Augumenting Timestamped Graphs with Event Information and Selectively Expanding Opinion Contexts
Our team explored several new approaches in the update and opinion summarization tasks in the Text Analysis Conference (TAC) 2008. For the update task, we refine our previous timestamped graph approach by incorporating information about temporal ordering of events in the articles, by using the publicly available Tarsqi toolkit. For the pilot opinion task, we utilize the provided opinion snippet...
متن کامل