A Noisy-Channel Approach to Question Answering Authors: Echihabi and Marcu Date: 2003 Presenters: Omer Percin Emin Yigit Koksal Ustun Ozgur IR 2013

Question Answering Approaches Matching same words  Does not always work Who is the leader of France? Hadjenberg, who is the leader of France Jewish Community... Solution: Some Kind of Transformation Needed

Noisy Channel Approach IDEA: Question is a noisy version of the Answer. ANSWER QUESTION NOISY CHANNEL MODEL

QA System Two Modules  IR Engine: Get relevant documents and their sentences  Answer Identification Module From these sentences, identify substrings S(A) as candidate answers For each substring (answer candidate) and sentence, calculate probability of obtaining the Question text using a Generative Model

Answer Identification Module HORIZONTAL CUTTER PERMUTER ANSWER MARKER FERTILIZER REPLACE R CANDIDATE SENTENCE QUESTION p1 p2p3 p4p5 P(Q|A) = p1 x p2 x p3 x p4 x p5 GENERATIVE MODEL

FERTILIZER REPLACER PERMUTER CUTTER ANSWER MARKER

Training and Testing Use the generative model Training:  Deterministic cutter  Answer known Testing: Given a Question  Exhaustive cutter (try each cut for each sentence)  Exhaustive answer marker (try each word as possible answer)  Generate probabilities: P(Q| Sentence+Cut+Answer)  Select Sentence+Cut+Answer combination with Max. P

Performance Not bad compared to systems with 10s modules, only 2 modules Beats QA-base in MRR on TREC datasets  ( vs 0.291) QA-base was state-of-art and ranked 2-7 in TREC in last 3 years (in 2003)