<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-0107">
  <Title>Latent Features in Automatic Tense Translation between Chinese and English Yang Ye + , Victoria Li Fossum SS</Title>
  <Section position="4" start_page="48" end_page="48" type="relat">
    <SectionTitle>
2 Related Work
</SectionTitle>
    <Paragraph position="0"> There is an extensive literature on temporal information processing. (Mani, et al., 2005) provides a survey of works in this area. Here, we highlight several works that are closely related to Chinese temporal information processing. (Li, 2001) describes a model of mining and organizing temporal relations embedded in Chinese sentences, in which a set of heuristic rules are developed to map linguistic patterns to temporal relations based on Allen's thirteen relations. Their work shows promising results via combining machine learning techniques and linguistic features for successful temporal relation classification, but their work is concerned with another type of temporal relationship, namely, the precedence-based temporal relation between a pair of events explicitly mentioned in text.</Paragraph>
    <Paragraph position="1"> A significant work worth mentioning is (Olsen et. al. 2001)'s paper, where the authors examine the determination of tense for English verbs in Chinese-to-English translation. In addition to the surface features such as the presence of aspect markers and certain adverbials, their work makes use of the telicity information encoded in the lexicons through the use of Lexical Conceptual Structures (LCS). Based on the dichotomy of grammatical aspect and lexical aspect, they propose that past tense corresponds to the telic (either inherently or derived) LCS. They propose a heuristic algorithm in which grammatical aspect markings supersede the LCS, and in the absence of grammatical aspect marking, verbs that have telic LCS are translated into past tense and present tense otherwise. They report a significant performance improvement in tense resolution from adding a verb telicity feature. They also achieve better performance than the baseline system using the telicity feature alone. This work, while alerting researchers to the importance of lexical aspectual feature in determination of tense for English verbs in Chinese-to-English machine translation, is sub-ject to the risk of adopting a one-to-one mapping between grammatical aspect markings and tenses hence oversimplifies the temporal reference problem in Chinese text. Additionally, their binary tense taxonomy is too coarse for the rich temporal reference system in Chinese.</Paragraph>
    <Paragraph position="2"> (Ye, et al. 2005) reported a tense tagging case study of training Conditional Random Fields on a set of shallow surface features. The low inter-annotator agreement rate reported in the paper illustrates the difficulty of tense tagging. Nevertheless, the corpora size utilized is too small with only 52 news articles and none of the latent features was explored, so the evaluation result reported in the paper leaves room for improvement.</Paragraph>
  </Section>
class="xml-element"></Paper>