Exploiting the bipartite structure of entity grids for document coherence and retrieval

TY - GEN

T1 - Exploiting the bipartite structure of entity grids for document coherence and retrieval

AU - Lioma, Christina

AU - Tarissan, Fabien

AU - Simonsen, Jakob Grue

AU - Petersen, Casper

AU - Larsen, Birger

N1 - Conference code: 2

PY - 2016/9/12

Y1 - 2016/9/12

N2 - Document coherence describes how much sense text makes in terms of its logical organisation and discourse flow. Even though coherence is a relatively difficult notion to quantify precisely, it can be approximated automatically. This type of coherence modelling is not only interesting in itself, but also useful for a number of other text processing tasks, including Information Retrieval (IR), where adjusting the ranking of documents according to both their relevance and their coherence has been shown to increase retrieval effectiveness [34, 37]. The state of the art in unsupervised coherence modelling represents documents as bipartite graphs of sentences and discourse entities, and then projects these bipartite graphs into one-mode undirected graphs. However, one-mode projections may incur significant loss of the information present in the original bipartite structure. To address this we present three novel graph metrics that compute document coherence on the original bipartite graph of sentences and entities. Evaluation on standard settings shows that: (i) one of our coherence metrics beats the state of the art in terms of coherence accuracy; and (ii) all three of our coherence metrics improve retrieval effectiveness because, as closer analysis reveals, they capture aspects of document quality that go undetected by both keyword-based standard ranking and by spam filtering. This work contributes document coherence metrics that are theoretically principled, parameter-free, and useful to IR.

AB - Document coherence describes how much sense text makes in terms of its logical organisation and discourse flow. Even though coherence is a relatively difficult notion to quantify precisely, it can be approximated automatically. This type of coherence modelling is not only interesting in itself, but also useful for a number of other text processing tasks, including Information Retrieval (IR), where adjusting the ranking of documents according to both their relevance and their coherence has been shown to increase retrieval effectiveness [34, 37]. The state of the art in unsupervised coherence modelling represents documents as bipartite graphs of sentences and discourse entities, and then projects these bipartite graphs into one-mode undirected graphs. However, one-mode projections may incur significant loss of the information present in the original bipartite structure. To address this we present three novel graph metrics that compute document coherence on the original bipartite graph of sentences and entities. Evaluation on standard settings shows that: (i) one of our coherence metrics beats the state of the art in terms of coherence accuracy; and (ii) all three of our coherence metrics improve retrieval effectiveness because, as closer analysis reveals, they capture aspects of document quality that go undetected by both keyword-based standard ranking and by spam filtering. This work contributes document coherence metrics that are theoretically principled, parameter-free, and useful to IR.

U2 - 10.1145/2970398.2970413

DO - 10.1145/2970398.2970413

M3 - Article in proceedings

SN - 978-1-4503-4497-5

SP - 11

EP - 20

BT - Proceedings of the 2016 ACM International Conference on the Theory of Information Retrieval

PB - Association for Computing Machinery

T2 - The 2nd ACM International Conference on the Theory of Information Retrieval

Y2 - 13 September 2016 through 16 September 2016

ER -