Semantic Frame Parsing for Information Extraction : the CALOR corpus

Semantic Frame Parsing for Information Extraction : the CALOR corpus Gabriel Marzinotto1,2, Jeremy Auguste2, Frederic Bechet2, Geraldine Damnati1, Alexis Nasr2 (1) Orange Labs, Lannion, France (2) Aix Marseille Univ, Universit´e de Toulon, CNRS, LIS, Marseille, France {gabriel.marzinotto, geraldine.damnati}@orange.com {jeremy.auguste, frederic.bechet, alexis.nasr}@lis-lab.fr Abstract This paper presents a publicly available corpus of French encyclopedic history texts annotated according to the Berkeley FrameNet formalism. The main difference in our approach compared to previous works on semantic parsing with FrameNet is that we are not interested here in full text parsing but rather on partial parsing. The goal is to select from the FrameNet resources the minimal set of frames that are going to be useful for the applicative framework targeted, in our case Information Extraction from encyclopedic documents. Such an approach leverages the manual annotation of larger corpora than those obtained through full text parsing and therefore opens the door to alternative methods for Frame parsing than those used so far on the FrameNet 1.5 benchmark corpus. The approaches compared in this study rely on an integrated sequence labeling model which jointly optimizes frame identification and semantic role segmentation and identification. The models compared are CRFs and multitasks bi-LSTMs. Keywords: Frame Semantic Parsing, LSTM, CRF 1. Introduction Semantic Frame parsing is a Natural Language Understand- ing task that involves detecting in a sentence an event or a scenario, called Frame, as well as all the elements or roles that can be associated to this event in the sentence, called Frame Elements. One of the most popular semantic frame model is the Berkeley FrameNet project developed by ICSI Berkeley (Baker et al., 1998). This model is composed of an inventory of Frames with, for each of them, a list of words, called Lexical Units (or LU), that can trigger a frame in a sentence. Besides, for each frame, a list of Frame Ele- ments (FE), core or optional, is defined. LUs are pairings of a word with a sense; Frame Elements are the components of a frame, represented by sequences of words in a sentence. Two kinds of parsing can be done with a Semantic Frame model: full text parsing where each word in a sentence is analyzed to check if it can trigger a frame; and partial pars- ing where only a subset of frames and LUs is considered, according to their relevance for a given applicative frame- work. Annotating all the possible LUs and frames in a sen- tence is a very difficult (and expensive) task for human an- notators, therefore there are very few corpora annotated this way. Moreover not many languages have such resources. Most of previous work in semantic frame parsing that has been done with a full text parsing approach have used the benchmark corpus FrameNet 1.5. Although the size of this benchmark is relatively large, a lot of frames have a very small number of occurrences in the corpus. This is due to the very large number of frames considered in the semantic model and this makes …

Content truncated to 500 words